Nanjundan's online Dictionary

Pega Decisioning Consultant - Mission Test Quiz & Answers

2021-12-05T20:20:00.004+05:30

The Pega Certified Decisioning Consultant (PCDC) certification is for professionals participating in the design and development of a Pega Customer Decision Hub™ solution. This certification ensures you have the skills to apply design principles of Next-Best-Action Designer, Decision Strategies, and Predictive Analytics.

The PCDC Version 8.5 & 8.6 exam includes multiple choice, scenario, and drag/drop questions. Here are the Pega Decisioning Consultant Mission Test Quiz & answers.

U+ Bank has a product eligibility matrix that defines what type of customers qualify for which offers when customers visit the bank's website.

Which two components in the Next-Best-Action Designer allows you to define these conditions? (Choose Two)

· Engagement Policy

The Engagement Policy component allows you to define the rules that control which actions are offered to which customers.

· Channels

· Arbitration

· Constraints

The Constraints component allows you to implement channel limits and constraints.

Through analysis of customer lifecycles, Next-Best-Action _______________.

· identifies global sales targets

· anticipates retention issues

In Pega Customer Decision Hub, the customer is central. Anticipating retention issues adds value for both the customer and the business.

· provides future sales reports

· provides fulfillment services

U+, a retail bank, does not want to annoy customers by offering them a mortgage refinance option if they have less than 5% to pay off on their loan, although it would be profitable for the bank. Which engagement policy condition best suits this requirement?

· Applicability

· Eligibility

· Suitability

Suitability conditions are the most flexible rules; they represent what the business should and shouldn’t do ethically and empathetically. The bank is being empathetic to the customer by not bothering them with a refinance offer, given they have only 5% left to pay off on their loan.

Myco, a telco, has recently implemented a project in which data plan offers are presented to qualified customers. Myco wants to understand the impact to revenue if the business introduces a new data plan offer. As a Decisioning Consultant, which simulation do you run to meet the requirement?

· Distribution Test

· Audience Simulation

· Pega Value Finder

· Pega Scenario Planner

Scenario Planner enables you to simulate “what-if” scenarios so that you can more accurately forecast results, optimize strategies, and explore potential tradeoffs.

What does a dotted line from a Group By component to a Filter component mean?

· The Filter component references a property in the Group By component.

If a component references a property from a different component, then a dotted line is automatically added to the strategy canvas. Note, this is just a visualization representation, it does not have anny other meaning in terms of values being copied, or execution order of the components.

· There is a one-to-one relationship between the Group By and Filter components.

· Information from the Group By component is copied over to the Filter component.

· Evaluate the Filter component first to evaluate the Group By component.

Reference module: Limiting action volume on outbound

An outbound run identifies 100 Standard Card offers, 50 on email and 50 on the SMS channel. If the above volume constraint is applied, how many actions will be delivered by the outbound run?

· 100

· 75

This is the total number of actions sent as a result of the outbound run. This is because the action-level volume constraint is configured with a limit of 75, and there are 75 remaining.

· 50 SMSes and 25 emails

· 50 emails and 25 SMSes

A bank is currently displaying a group of mortgage offers to its customers on their website. The bank wants to suppress the mortgage group for 1 month if a customer ignores three mortgage offers within that group. How do you define the suppression rule for this requirement?

· Suppress a group of actions for 30 days if there are 3 impressions for the web channel without a click.

This rule definition suppresses a group of actions if 3 impressions are recorded in the web channel.

· Suppress an action for 30 days if there are 3 impressions for any channel without a click.

· Suppress an action for 30 days if there are 3 rejects for web channel.

· Suppress a group of actions for 30 days if there are 3 rejects for any channel.

The arbitration factor that allows you to assign financial values to actions is called: _________________________.

· business levers

· context weighting

· action value

Action value allows the business to assign financial values to offers and prioritize high-value offers over low-value ones.

· propensity

Which statement is true about email treatments?

· You must always embed the images in the email.

· When you design emails using external tools, you cannot include Pega-specific personalization tags.

· When you use a seed list to test an email, the personalization attributes do not appear in the received email.

· You can personalize the email subject, for example, Dear <customer name>.

You can personalize the email subject using the same construct as the email body, the .Customer.<property name>.

A bank has chosen an email service provider to deliver the offer messages selected by Pega Customer Decision Hub. The service provider prefers that the bank uploads a file per batch of customers to a cloud storage location, either on Microsoft Azure or Amazon S3. As a consultant working on the project representing the bank, what is your response?

· Action details will be written to the local filesystem by default. But we will write an external process to transfer them to the cloud.

· Action details can be directly written to either of those cloud storage solutions.

Both Amazon S3 and Microsoft Azure are valid repositories for a file template.

· Action details can only be transferred via secure FTP.

· Action details can be written directly to Amazon S3 but not Microsoft Azure.

Reference module: Detecting unwanted bias

MyCo, a telco, has introduced mobile data packages for students. As a policy, MyCo does not want to discriminate based on gender when presenting the offers. As a Decisioning Consultant, how do you configure the ethical bias policy to allow no bias?

· No Detection

· 1 Rate Ratio

When a property is set to a 1 Rate Ratio, no bias is allowed.

· 0.9-1.11 Rate Ratio

· 0.5-2 Rate Ratio

As a Decisioning Consultant, you have just implemented a project to present mortgage offers to customers on their self-service portals. The bank asks you to pull data on the distribution of the offers to well-engaged, under-engaged, or not-engaged customers. Which simulation do you run to get the required information?

· Audience simulation

· Pega Scenario Planner

· Distribution Test

· Pega Value Finder

Value Finder allows the business to engage more empathetically by identifying and profiling underserved customers, then suggesting actions for improvement.

Enrichment decision components provide the ability to ______________________.

· set customer properties

· enrich a decision strategy with comments

· set a text value to a strategy property

To set a text or numeric value to an action property you use a Set Property component from the enrichment category.

· filter actions based on priority and relevance

What is best practice for designing an action flow?

· Always configure an action with its own flow.

· When designing a flow to be reused across multiple actions, use the Specify Treatment option to configure it with a specific treatment.

· Limit the number steps per channel to 3.

Every additional step taken in the action flow is a missed opportunity to let the Pega brain decide the Next-Best-Action.

· When creating an action to be used as a flow template, set its availability to Always.

U+ Bank, a retail bank, is working on implementing a project in which credit card offers are presented to qualified customers the customers they log in to the web self-service portal. The bank wants to ensure there that is no bias identified in its engagement policies.

Arrange the following steps in the correct order to implement this task.

Dropzone 1 of 4.

Configure ethical bias policy

Dropzone 2 of 4.

Create ethical bias simulation

Dropzone 3 of 4.

Select the Strategy & Audience for Simulation

Dropzone 4 of 4.

Execute Simulation and analyse the outcome

Reference module: Creating eligibility rules using customer risk segments

U+ bank uses a decision table to return a label for a customer. Examine this decision table and select which label is returned for a customer with a credit score of 115 and an average balance of 15000.

· D

· C

The credit score is 115, so it satisfies the >= condition. The value 15000 satisfies the average balance condition. Remember the decision table evaluation stops when a condition is satisfied.

· B

· A

A bank is currently sending promotional emails related to credit card offers to qualified customers. Now the bank wants to prevent overexposure to these offers. As a part of this effort, the bank wants to avoid sending the same promotional offer email for the next 60 days if the email was rejected twice by the customer in the last 30 days. How do you define the suppression rule for this contact policy?

· Suppress a group of actions for 60 days if there are 2 rejects in the email channel in the last 30 days.

· Suppress an action for 60 days if there are 2 rejects in any channel in the last 30 days.

· Suppress a group of actions for 60 days if there are 2 rejects in any channel in the last 30 days.

· Suppress an action for 60 days if there are 2 rejects in the email channel in the last 30 days.

This rule definition suppresses an action for a given time period in the email channel.

Which two of the following statements are true about Scenario Planner? (Choose Two)

· Helps optimize strategies to hit specific business goals

Pega Scenario planner helps the business make adjustments to align projected reach with business priorities.

· Projects estimated value of the subsequent next-best-action run

Pega Scenario Planner projects the estimated value that the subsequent next-best-action run creates by using the selected configuration.

· Shows the distribution of customers across different groups

· Identifies engagement policy conditions with bias

U+ Bank, a retail bank, recently implemented a project in which credit card offers are presented to qualified customers when the customers log in to the web self-service portal. The bank now plans to amend its engagement policy conditions. As a Decisioning Consultant, which simulation do you run to check if the conditions are too broad or narrow for your requirements?

· Ethical Bias Check

· Audience simulation

Audience simulation tests the configuration of engagement policies against an audience.

· Pega Scenario Planner

· Persona Testing

A bank has several credit card offers defined under the sales issue / credit card group. The card_type action property for some of the cards is set to VISA and for others to Mastercard. The bank wants to limit the total number of VISA cards sent via email in an outbound run. How do you implement this requirement?

· Define a group-level constraint to limit all credit cards.

· Define a property constraint based on the value of the card_type action property.

A property constraint allows you to limit the action volume based on the value of an action property.

· Move the VISA and Mastercard actions to separate groups, then define two separate volume constraints

· Define an action-level constraint for each of the actions separately.

Pega Decisioning Consultant - 1:1 Customer Engagement Optimization Module Quiz & Answers

2021-12-05T20:07:00.004+05:30

The PCDC Version 8.5 & 8.6 exam includes multiple choice, scenario, and drag/drop questions. Here are the Pega Decisioning Consultant Mission Test Quiz & answers.

Drag the words into the correct boxes.

Audience Simulation

helps test the configuration of engagement policies with respect to an audience.

Pega Value Finder

allows the business to engage more empathetically by identifying and profiling “under-served” customers, then suggesting actions for improvement.

Pega Scenario Planner

enables you to simulate “what-if” scenarios so they can more accurately forecast results, optimize strategies, and explore potential tradeoffs.

Ethical Bias Check

helps test the engagement policies for unwanted discrimination.

Distribution Test

outputs the results to a database table and presents the results using out-of-the-box simulation reports.

Which two of these statements is true about Value Finder? (Choose Two)

· Identifies opportunities for improvement

Value Finder helps find the top opportunities for improvement by identifying the most significant gaps in the strategy.

· Identifies engagement policy conditions with bias

· Shows the distribution of under-served customers across different groups

Value Finder helps visualize the distribution of well-engaged, under-engaged, and not engaged customers.

· Projects estimated value of the subsequent next-best-action run

U+, a retail bank, runs an audience simulation with only engagement policies in scope (no arbitration) to understand how its engagement policy conditions perform for its sampled customers. The image above shows the results of this simulation. What do the action-level numbers indicate?

· Number of times an action was presented as the top offer

· Number of customers who receive a particular action as the top action

· Number of times an action was presented to customers

· Number of customers who qualify for a particular action

Running an audience simulation with only engagement policy in scope gives the total number of customers who qualify to receive a particular action.

As a Decisioning consultant, you are tasked with running an audience simulation to test the engagement policy conditions. Which statement is true when the simulation scope is: Audience simulation with engagement policy and arbitration?

· The number of times an action was presented to customers is displayed.

· The number of customers who receive more than one action is displayed

· The number of customers who receive an action more than once is displayed.

· The number of customers who receive a particular action as the top action is displayed.

Running an audience simulation with engagement policy and arbitration in scope provides the total number of customers who qualify to receive a particular action.

Myco, a telco, wants to present their customers with new credit card offers – the Diamond card, the Platinum card, and the Gold card – on their web portal. As a decisioning consultant, you want to determine which will be the best performing action by running a distribution test. In this scenario, which report will test this requirement?

· Action Distribution Report

· Bias Report

· Action Priority Report

The action priority report shows the average priority of each action.

· Channel Report

U+, a retail bank, recently implemented a project in which credit card offers are presented to qualified customers when they log in to the web self-service portal. The bank does not want any bias except to satisfy the eligibility condition Age >=18. As a Decisioning Consultant, how will you configure the ethical bias policy to allow a minimum bias on age?

· 0.1 Gini

When a property is set to 0.1 Gini, a minimum bias is allowed.

· 0.7 Gini

· No Detection

· 0 Gini

As a Decisioning Consultant, you are tasked with configuring the ethical bias policy. Which context do you need to select to add bias fields?

· Action Group

· Customer

Customer context contains the customer properties such as age and gender on which bias testing can be done.

· Treatment

· Action

U + Bank, a retail bank, has applied business weight to their credit card offers to manually nudge the offers. The bank analyzes the effect of the change in Scenario Planner. The following image shows the Projected reach and responses of the cards in the comparison mode.

How many customers are likely to accept the Standard card?

· 21

Projected responses represent the number of customers who are likely to accept the offer.

· 115

· 79 (115-36)

· 14 (21-7)

U+ Bank, a retail bank, completed an implementation to present Credit Card offers to customers on their self-service portals. You want to estimate the business value that the subsequent next-best-action run creates using the selected configuration. Which simulation do you run to get the required information?

· Distribution Test

· Pega Scenario Planner

Scenario Planner enables you to simulate “what-if” scenarios so that you can more accurately forecast results, optimize strategies, and explore potential tradeoffs.

· Audience Simulation

· Pega Value Finder

· Persona Testing

· Audience simulation

Audience simulation tests the configuration of engagement policies against an audience.

· Pega Scenario Planner

· Ethical Bias Check

Myco, a telco, is working on implementing a project in which post-paid offers are presented to qualified customers. In the build stage of the ideation, the business wants to look for new opportunities to improve marketing. As a Decisioning Consultant, which simulation do you run to meet the requirement?

· Distribution Test

· Pega Value Finder

Value Finder finds top opportunities to improve gaps in strategies and suggests actions for improvement.

· Pega Scenario Planner

· Audience Simulation

· Pega Scenario Planner

· Pega Value Finder

Value Finder allows the business to engage more empathetically by identifying and profiling underserved customers, then suggesting actions for improvement.

· Distribution Test

· Audience simulation

Which two of the following statements are true about Scenario Planner? (Choose Two)

· Helps optimize strategies to hit specific business goals

Pega Scenario planner helps the business make adjustments to align projected reach with business priorities.

· Identifies engagement policy conditions with bias

· Shows the distribution of customers across different groups

· Projects estimated value of the subsequent next-best-action run

Pega Scenario Planner projects the estimated value that the subsequent next-best-action run creates by using the selected configuration.

Reference module: Detecting unwanted bias

· No Detection

· 0.9-1.11 Rate Ratio

· 1 Rate Ratio

When a property is set to a 1 Rate Ratio, no bias is allowed.

· 0.5-2 Rate Ratio

Which two of the following statements are true about Value Finder? (Choose Two)

· Identifies engagement policy conditions with bias

· Provides recommendations to loosen strict conditions

Value Finder identifies if a condition is too broad or narrow and provides recommendations to adjust the condition to serve more customers.

· Shows the distribution of under-served customers across different groups

Value Finder helps visualize the distribution of well-engaged, under-engaged, and not engaged customers.

· Projects estimated value of the subsequent next-best-action run

· Distribution Test

· Audience Simulation

· Pega Scenario Planner

Scenario Planner enables you to simulate “what-if” scenarios so that you can more accurately forecast results, optimize strategies, and explore potential tradeoffs.

· Pega Value Finder

As a Decisioning Consultant, you are tasked with running an audience simulation to test the engagement policy conditions. Which of following statements is true when the simulation scope is Audience simulation with engagement policy and arbitration?

· The number of customers who receive an action more than once is displayed.

· The results help optimize strategies to meet specific business goals.

An audience simulation run helps identify if an engagement policy condition is too broad or too narrow to achieve the required business goals.

· The number of times that an action is presented to customers is displayed.

· The number of customers who receive more than one action is displayed.

Pega Decisioning Consultant - Always-On Outbound Customer Engagement - Module Quiz & Answers

2021-12-05T20:04:00.003+05:30

The PCDC Version 8.5 exam includes multiple choice, scenario, and drag/drop questions. If multiple answers are required, the text states how many responses are needed.

U+ Bank has recently implemented a cross-sell on the web microjourney and is satisfied with the results. The bank now wants these Next-Best-Action recommendations to be delivered via outbound communication channels. Select two outbound channels that U+ bank can use to deliver Next-Best-Action recommendations. (Choose Two)

· Google

· Contact Center

· Mobile application

· SMS

SMS is one of the outbound channels.

· Email

Email is one of the outbound channels.

In the primary schedule recurrence configuration, what does the Refresh the audience option mean?

· It triggers an external ETL (Extract-Transform-Load) process to refresh the audience.

· It picks a different audience sample with a similar profile for the run.

· It ensures that a new audience is selected for each run.

· It ensures that the latest customer information is used before running the schedule.

The latest customer information is used from the system before the outbound schedule is run to maximize the relevance of Next-Best-Action recommendations.

A marketer created a segment as the starting population for the outbound schedule. In Options and Schedule, she enabled the Refreshable Segment option. What does this option do?

· It allows other segments to automatically refresh the current segment when the other segments that reference it are run.

A refreshable segment is one that can be refreshed by another segment when it is executed.

· A refreshable segment is only populated when another segment refreshes it.

· It automatically refreshes all segments referenced by it.

· Refreshable segments must not be used as the starting population in an always-on outbound schedule.

U+ Bank is currently running outbound communications for home loan offers and credit cards. They have added five new actions to the Credit Cards group. They would like to enable these actions in the email channel. What are the two minimum configurations that must be made? (Choose Two)

· Configure each action to reference its own action flow.

· Configure each action to reference a single action flow.

You can create one action flow and reuse it across all actions using the dynamic flow template.

· Enable the email channel in Next-Best-Action->Channels.

o This is one possible answer.

· Configure each action with an email treatment.

Each action that needs to be enabled in the email channel must be configured with an email treatment.

· Configure one action with an email treatment.

For a limited time period, a bank wants to avoid sending promotional emails related to credit card offers to a customer if they have already received one. Which rule do you need to define to implement this business requirement?

· Applicability rules

· Suppression policy

Suppression policies are used to limit when and for how long an action or group of actions should be shown to a customer.

· Customer contact limits

· Volume constraints

A volume constraint is configured to apply constraints to actions as a group rather than for each action individually. A customer qualifies for 3 actions, and the volume limit on the top-ranked action is above zero, the limits on the 2 lower-ranked actions have been reached. Given this scenario, how many actions will be selected for the customer in the outbound run?

· 3

When a volume constraint is configured at a group level, and a customer qualifies for multiple actions, all actions are selected for the customer provided that the limit on the top action has not been reached.

· 0

· 2

· 1

A bank would like to write action details to a file so that it can be shared with a third-party email distributor. The bank has instructed their consultant to ensure the action details are finalized at the end of each run. In this context, what does finalization mean?

· All data in the file is the result of all the runs.

· All data in the file is the result of a single run.

By finalizing at the end of each run, you ensure that all data in the file is the result of a single run.

· All data in the file is the result of the first run.

· All data in the file is the result of the last five runs.

A U+ bank customer tries to initiate a fund transfer. Due to a slow internet connection, the transfer ends abruptly. The bank then sends an email with a link to continue the incomplete transaction. Which type of outbound interaction is this?

· Scheduled update

· Security event

· Priority communication

· Customer event

When a customer event is detected that is of significance to the business, data is received via the event stream, the brain then evaluates the situation and sends the resulting Next-Best-Action.

Traditionally, segments were used to identify the target audience for a campaign. In the always-on approach, segments translate into _________________.

· engagement policies and AI

Engagement policies define a set of rules that make certain actions available for certain customers. AI is used to prioritize and choose the best actions based on what is relevant for the customer right now.

· segmentation

· contact policies

· actions and treatments

U+ Bank’s marketing department currently promotes various credit card offers by sending emails to qualified customers. Now the bank wants to limit the number of emails sent to their customers irrespective of past outcomes with a particular offer and customer. Which of the following options allows you to implement this business requirement?

· Suppression policies

· Suitability rules

· Volume constraints

· Customer contact limits

Customer contact limits keep an action from reaching a customer on a specific channel, irrespective of past outcomes with that offer and customer.

· Suppress an action for 60 days if there are 2 rejects in any channel in the last 30 days.

· Suppress a group of actions for 60 days if there are 2 rejects in the email channel in the last 30 days.

· Suppress a group of actions for 60 days if there are 2 rejects in any channel in the last 30 days.

· Suppress an action for 60 days if there are 2 rejects in the email channel in the last 30 days.

This rule definition suppresses an action for a given time period in the email channel.

Reference module: Limiting action volume on outbound

An outbound run identifies 100 Standard Card offers, 50 on email and 50 on the SMS channel. If the above volume constraint is applied, how many actions will be delivered by the outbound run?

· 75

This is the total number of actions sent as a result of the outbound run. This is because the action-level volume constraint is configured with a limit of 75, and there are 75 remaining.

· 100

· 50 SMSes and 25 emails

· 50 emails and 25 SMSes

A bank has been running traditional marketing campaigns for many years. One such campaign sends an offer email to qualified customers on day 1. On day 3, it sends a reminder email to customers who haven't responded to the first email. On day 7, it sends a second reminder to customers who haven't responded to the first two emails. If you were to re-implement this requirement using the always-on outbound customer engagement paradigm, how would you approach this scenario?

· Configure the primary schedule to run daily and let the AI choose the best action from all the actions that a customer qualifies for based on engagement policies.

You should define engagement policies to ensure that a customer qualifies for relevant offers, and let the AI choose the best offer at any given time.

· Create three segments to identify the target audience for each of the three offer emails - day 1, day 3 and day 7. Setup three schedules per day targeting each of the three segments.

· Create an action with a flow that contains 3 Send Email shapes, one for each email. Set appropriate wait times between the shapes.

· Configure a primary schedule for the original offer email and setup an ad-hoc or emergency schedule to send reminder emails.

U+ Bank currently uses Next-Best-Action Designer to manage 1:1 customer engagement in the web channel. The bank would like to promote the same offers in email. Which two additional configurations are needed in Next-Best-Action Designer to promote the offers in email? (Choose Two)

· Setup real-time container triggers to communicate with the email server.

· Configure the arbitration to boost prioritization of actions meant for email.

· Ensure that the email channel is enabled.

The email channel must be enabled under Channels to ensure that email treatments are selected.

· Define the primary schedule.

The primary schedule must be defined.

· Create a separate issue and group business structure in the taxonomy that is specific to email actions.

Which two of these statements are true about creating segments? (Choose Two)

· When building the segment, if you want to know the count resulting from the criteria defined so far, the only way to do this is by running the segment.

· In a segment you can reference customer properties OR another segment, but not both.

· The result of a criteria group can be combined with the result above it using AND and OR operators.

· A segment run can be triggered by the Next-Best-Action outbound schedule.

When the Refresh the Audience option is set in the primary schedule, every outbound run triggers a segment run.

· The list of customers in a segment can be viewed from within the segment

The list of customers can be viewed using the Show Customers button.

Reference module: Defining an action for outbound

Which statement is true about email treatments?

· You must always embed the images in the email.

· You can personalize the email subject, for example, Dear <customer name>.

You can personalize the email subject using the same construct as the email body, the .Customer.<property name>.

· When you use a seed list to test an email, the personalization attributes do not appear in the received email.

· When you design emails using external tools, you cannot include Pega-specific personalization tags.

What is best practice for designing an action flow?

· When creating an action to be used as a flow template, set its availability to Always.

· When designing a flow to be reused across multiple actions, use the Specify Treatment option to configure it with a specific treatment.

· Limit the number steps per channel to 3.

Every additional step taken in the action flow is a missed opportunity to let the Pega brain decide the Next-Best-Action.

· Always configure an action with its own flow.

· Define a group-level constraint to limit all credit cards.

· Define an action-level constraint for each of the actions separately.

· Define a property constraint based on the value of the card_type action property.

A property constraint allows you to limit the action volume based on the value of an action property.

· Move the VISA and Mastercard actions to separate groups, then define two separate volume constraints

· Action details can only be transferred via secure FTP.

· Action details will be written to the local filesystem by default. But we will write an external process to transfer them to the cloud.

· Action details can be written directly to Amazon S3 but not Microsoft Azure.

· Action details can be directly written to either of those cloud storage solutions.

Both Amazon S3 and Microsoft Azure are valid repositories for a file template.

Pega Decisioning Consultant - Cross-Sell on the Web Extended Module Quiz & Answers

2021-12-05T19:58:00.004+05:30

Pega Decisioning Consultant - Cross-Sell on the Web Extended Module Quiz & Answers

U+ Bank wants to leverage Pega Customer Decision Hub's Next Best Action capability to promote new offers to each customer who visits the website based on eligibility. For this requirement, the bank needs to define several complex eligibility criteria.

As a decision consultant, how would you configure this requirement?

· Create new decision strategies

Since the requirement calls for complex eligibility criteria, new decision strategies need to be created.

· Make changes to the Next-Best-Action Framework decision strategy

· Configure suppression rules in Next-Best-Action Designer

· Use Prediction Studio to configure the requirement

A strategy designer has created 10 actions in the Sales/Credit Cards group and 10 actions in the Sales/Mortgages group. He would like to import all 10 actions from the Credit Cards group and only two actions from the Mortgage group into one decision strategy. What is the minimum number of Proposition Data components he needs to use in his strategy?

· three

You can use one Proposition Data component to import all 10 credit card actions, and two additional Proposition Data components to import the two mortgage actions.

· one

· two

· twelve

U+ Bank wants to offer a 10% discount for customers whose CLV value is higher than 400. Which strategy component should you use to meet the new requirement?

· Set Property

Set Property components enrich data by adding information to other components, allowing you to define personalized content that will be delivered with a decision.

· Group By

· Filter

· Prioritize

U+ Bank, a retail bank, offers the Standard card, the Rewards card and the Rewards Plus card to its customers. The bank wants to display the banner for the offer that each customer is most likely to click; therefore, their Arbitration uses Propensity from the AI models. If you are debugging the Next-Best-Action decision strategy, which strategy component will show you if the result of the Arbitration is correct?

· Group By

· Filter

· Prioritize

Prioritize components rank the strategy results from the components that connect to them based on the value of a strategy property, or a combination of strategy properties.

· Set Property

U+ Bank has several eligibility criteria defined using an eligibility strategy. The eligibility strategy uses a scorecard rule to determine the customer credit score. The bank wants to update the scorecard to include customer income in the credit score calculations. How do you implement this change?

· Recreate the scorecard rule from scratch.

· Change both the scorecard as well as the decision strategy using the scorecard.

· Change only the decision strategy using the scorecard.

· Update only to the existing scorecard.

The scorecard’s internal calculations do not affect the strategy.

A bank is currently doing cross-sell on the web by showing various credit cards to its customers. Due to the credit limits of each card, the bank wants to present credit cards only to suitable customers who have a credit score greater than 500. Which component helps you to calculate a customer’s credit score?

· Filter

· Results

· Set Property

· Scorecard

Scorecard components are used to calculate a customer’s credit score based on the customer properties.

A bank developed a scorecard to automate the loan approval process. In a decision strategy, how do you use the raw score value computed by the scorecard?

· Map a new property in the Score Mapping tab.

Score mapping allows you to map the score value, computed by the scorecard, to a property, for example, CreditScore.

· Use the PropertyHasValue function.

· Use the pxSegment property.

· Use the pyOutcome property.

A bank developed a scorecard to automate the loan approval process. In the scorecard rule, there is a classification implemented using three score bands: Not Approved, Refer to Manager, and Approved. Which property allows you to use the result of this classification in a decision strategy?

· PropertyHasValue

· pyOutcome

· pxSegment

The pxSegment property contains the result of the scorecard calculation such as Not Approved, Refer to Manager, or Approved.

· pyPropensity

U+ bank uses a decision table to return a label for a customer. Examine the above decision table and select which label is returned for a customer with a CLV score of 550 and a LOW propensity to leave.

· A

The CLV is 550. Since a test on an empty CLV value returns true, this means both conditions (>= and <= condition) from the first row are satisfied. The value LOW satisfies the propensity to leave. Since both conditions, the CLV property and the propensity to leave property, are satisfied, and because the decision table evaluation stops when the first condition is satisfied, the first result is returned.

· B

· C

· D

U+ Bank promotes credit card offers on its website and uses Pega Customer Decision Hub to personalize the offer for every customer. Now, the bank wants to lower the number of customers that leave the bank by showing a proactive retention offer to high churn risk customers instead. As an NBA analyst, you are tasked with creating a new applicability setting to comply with the new business rule. Which business issue or issues do you modify?

· The Sales issue

· The Retention issue

· No modification is required

· The Sales issue and the Retention issue

The business rule is twofold

MyCo, a telecom company, has a new requirement to track customer responses over a period of 20 days. What do you need to create to start tracking customer responses for the given period of time?

· Data Join component

· Interaction History component

· Interaction History summary rule

The Interaction History summary rule tracks customer responses such as impressions and clicks over a period of time.

· Group By component

A telco wants to add a contact policy that will suppress an action for 30 days if it was rejected twice in any channel in the last 15 days. How do you define the suppression rule for the contact policy?

· Suppress an action for 30 days if there are 2 rejects for any channel in the last 15 days

This rule definition suppresses an action for a given time period in any channel.

· Suppress a group of actions for 30 days if there are 2 rejects for any channel in the last 15 days

· Suppress an action for 30 days if there are 2 rejects in the web channel in the last 15 days

· Suppress a group of actions for 30 days if there are 2 rejects in the web channel in the last 15 days

Reference module: Creating and understanding decision strategies

In a decision strategy, to use a customer property in an expression, you _______________.

· prefix the property with the keyword Customer

In order to access a customer property you need to prefix the property with “Customer.”. Example¤ Customer.Age.

· define the Customer page in Pages and Classes

· use the property as defined without a prefix

· define the property as a strategy property

Reference module: Creating and understanding decision strategies

Enrichment decision components provide the ability to ______________________.

· set a text value to a strategy property

To set a text or numeric value to an action property you use a Set Property component from the enrichment category.

· filter actions based on priority and relevance

· enrich a decision strategy with comments

· set customer properties

Reference module: Creating and understanding decision strategies

In a Prioritize component, the top action can be determined based on the value of _______________.

· the propensity

To prioritize actions, you use a prioritization expression in a Prioritize component. Although technically Customer.Value is a valid numeric expression, it would not make sense to prioritize on this becuase all actions would have the same Customer.Value.

· average margin of all actions

· Primary.Income

· Customer.Value

Reference module: Creating and understanding decision strategies

What does a dotted line from a Group By component to a Filter component mean?

· Information from the Group By component is copied over to the Filter component.

· There is a one-to-one relationship between the Group By and Filter components.

· The Filter component references a property in the Group By component.

· Evaluate the Filter component first to evaluate the Group By component.

Reference module: Creating and understanding decision strategies

MyCo, a mobile company, wants you to calculate the total revenue of three new actions offered in the first quarter. What do you configure to compute the total revenue?

· A single Set Property component

· Three Set property components

· Three Group By components

· A single Group By component

To compute the total revenue, you use a single Group By action and set a property using the aggregation function sum.

Reference module: Creating engagement strategies using customer credit score

MyCo, a mobile company, uses a scorecard rule in a decision strategy to compute the postpaid credit limit for a customer. MyCo updated their scorecard to include a new property in the calculation: customer annual income.As a Strategy Designer, what changes do you need to make to the decision strategy for the updated scorecard to take effect?

· Remap the <Customer.annual customer income> property in the decision strategy.

· Configure a new proposition filter in the strategy to filter on annual customer income.

· No change required.

Since you only want to change the scorecard calculation, you do not need to make any changes to the decision strategy. You just need to alter the calculation in the scorecard rule itself.

· Add a Set-Property component to set the annual customer income.

Reference module: Adding more tracking time periods for contact policies

A bank is currently displaying a group of mortgage offers to its customers on their website. The bank wants to suppress the mortgage group for 15 days if a customer ignores three offers from the mortgage group. How do you define the suppression rule for this requirement?

· Suppress an action for 15 days if there are 3 rejects for web channel.

· Suppress a group of actions for 15 days if there are 3 rejects for any channel.

· Suppress a group of actions for 15 days if there are 3 impressions for the web channel without a click.

This rule definition suppresses a group of actions if 3 impressions are recorded in the web channel.

· Suppress an action for 15 days if there are 3 impressions for any channel without a click.

Reference module: Creating eligibility rules using customer risk segments

U+ Bank uses a decision table to return a label for a customer. Examine this decision table and select which label is returned for a customer with a credit score of 115 and an average balance of 15000.

· D

· A

· C

The credit score is 115, so it satisfies the >= condition. The value 15000 satisfies the average balance condition. Remember the decision table evaluation stops when a condition is satisfied.

· B

Reference module: Leveraging predictive model

U+, a retail bank, wants to show a retention offer to customers who are likely to leave the bank in the near future based on historical customer interaction data. Which type of model do you use to implement this requirement?

· A text analytics model

· A predictive model

Predictive models require historical data that contains the customer behavior you want to predict.

· An adaptive model

· An entity model

Pega Decisioning Consultant - Cross-Sell on the Web Module quiz & Answers

2021-12-05T19:56:00.002+05:30

Pega Decisioning Consultant - Cross-Sell on the Web Module quiz & Answers.

U+ Bank's marketing department wants to promote various auto loan offers to qualified customers on its website by using the Pega Customer Decision Hub™. The bank wants to show the offers on the customer's account page when customers log in to their account. The bank has defined several conditions customers must satisfy to see these auto loan offers.

As a decisioning consultant, which two of the following configurations do you implement to achieve the business requirement? (Choose Two)

· Set up the business structure

To achieve the business requirement using Customer Decision Hub, you must first set up the business structure.

· Create a segment

· Define contact policy rules

To express the bank's conditions, you often use contact policies.

· Create a decision strategy

· Send promotional emails

MyCo, a telecommunications company, wants to implement one-to-one customer engagement using Pega Customer Decision Hub™. Which of the following real-time channels can the company use to present Next-Best-Actions? (Choose Three)

· SMS

SMS is a valid channel.

· Traditional television advertisements

· A retail store

In a retail store, a customer service representative can use Next-Best-Action recommendations to provide one-to-one customer engagement.

· Billboard on the company building

· The call center

In a call-center, a customer service representative can use Next-Best-Action recommendations to provide one-to-one customer engagement.

Which statement best describes the goal of Next-Best-Action?

· Balance customer needs with business objectives.

Next-Best-Action weighs customer needs against business objectives to optimize decisions based on priorities set by the business. This is the goal of Next-Best-Action.

· Ensure that the customer is always given a desirable offer.

· Ensure that every customer receives the same action.

· Provide insight into business processes.

Next-Best-Action ensures that communication between the business and the customer is__________ and __________. (Choose Two)

· timely

The artificial intelligence embedded in the Next-Best-Action platform ensures that every message is relevant and timely, so the customer can take immediate action.

· contextual

The artificial intelligence embedded in the Next-Best-Action platform ensures that every message is relevant and contextual, so the customer is more likely to respond.

· uniform and generic

· free of jargon

In an organization, customer actions are applicable to various business issues. What is the best way to organize them?

· Into a three-level hierarchy: Business issue > Group > Actions

The business structure is organized into a three-level hierarchy.

· Into a two-level hierarchy: Group > Actions

· Into a simple flat list including all actions

· Into a two-level hierarchy: Business issue > Actions

A bank wants to leverage Pega Customer Decision Hub’s Next-Best-Action capability to promote new offers to each customer on their website. Which artifact do you need to configure to manage the communication between the Customer Decision Hub and external channels?

· Event strategy

· Real-time Event

· Geofence

· Real-time Container

Real-time Containers manage communication between Pega Customer Decision Hub and external channels.

A bank wants to present the Rewards Card offer on the top right of the customers’ account page when they log in. Select the placement type of the treatment design.

· Carousel

· Footer bar

· Hero

· Tile

Tile type allows you to display an offer at a defined location on the account page.

MyCo, a telco, wants to offer a Fiber Optic Cable package only to customers who live in towns that have fiber optic cable available. Which engagement policy condition best suits this requirement?

· Suitability

· Applicability

· Eligibility

Eligibility conditions are used to define strict rules that cannot be bypassed. This condition must be a strict rule, as customers in towns without fiber optic cable cannot use this offer.

U+, a retail bank, does not want to offer a Gold card to customers who already have a Platinum card. Which engagement policy condition best suits this requirement?

· Suitability

· Applicability

Applicability conditions are flexible rules used to limit which offers are presented to customers. In this case, if a customer owns a Platinum card, U+ does not want to waste their time offering the Gold card, unless they explicitly ask for it.

· Eligibility

U+, a retail bank, has recently implemented a project in which credit card offers are presented to qualified customers when they log in to the web self-service portal. They have unit-tests in place using persona tests. The bank has recently added new engagement policy conditions to present credit cards to qualified customers and re-executed the tests. They see failures in the tests. What do they do next?

· Revert the engagement policy rules so that the persona tests not failing

· Analyze test case failures, change them and re execute until everything is green

Personas are predefined keeping in mind the business requirements. These persona are used to test the results of the next-best-action strategy framework defined. Hence all the tests should pass.

· Accept that some of the tests are failing because of the changes

· Remove the failing tests to ensure everything is green

A bank wants to automatically pause actions that are shown too often for a specific time period. Which rules do you need to define?

· Applicability rules

· Suitability rules

· Suppression rules

Suppression rules are used to limit when and for how long an action or group of actions should be shown to a customer.

· Eligibility rules

A bank wants to add a contact policy that will suppress an action for 20 days if it was rejected twice in any channel in the last 30 days. How do you define the suppression rule for the contact policy?

· Suppress an action for 20 days if there are 2 rejects in the web channel in the last 30 days.

· Suppress an action for 20 days if there are 2 rejects for any channel in the last 30 days.

This rule definition suppresses an action for a given time period in any channel.

· Suppress a group of actions for 20 days if there are 2 rejects in the web channel in the last 30 days.

· Suppress a group of actions for 20 days if there are 2 rejects for any channel in the last 30 days.

A bank wants to sell more mortgages in the fourth quarter and is willing to offer mortgages even in situations where a credit card may have created more value. Which arbitration factor do you configure to implement this requirement?

· Suitability

· Eligibility

· Applicability

· Business levers

Business levers allow you to manually assert some level of control over the prioritization of offers.

Myco, a telecommunications company, has introduced new data plans for students. The company wants to present offers to customers based on the responses of a test group that already received the offer. Which arbitration factor do you configure to implement this requirement?

· Propensity

Propensity is the likelihood of a customer responding positively to an offer. This is calculated by artificial intelligence (AI).

· Business levers

· Action value

· Context weighting

MyCo, a telecommunications company, wants to present customers with a free 2GB data offer when contacting the call center for mobile number portability. Which arbitration factor do you configure to implement this requirement?

· Propensity

· Business levers

· Context weighting

Context weighting enables the Pega Customer Decision Hub to consider the situational context of an offer when prioritizing it.

· Action value

U+ Bank realizes that customers have ignored a particular mortgage offer. As a result, the bank wants to offer the action 30% more frequently. Which arbitration factor do you configure to implement this requirement?

· Action weighting

Action weighting allows the business to manually assert some level of control over the prioritization of an offer.

· Action value

· Context weighting

· Business purpose weighting

Myco, a telco, currently promotes 24-month contracts with a free handset plus data plan, for example, MyPhone 11 and unlimited calls and data. The business structure has a sales issue/plans group that contains all actions, which are currently handsets.

Now, the company wants to introduce some new plans without handsets. So, the term handsets no longer applies to the new actions. At what level in the hierarchy can you rename the plans to reflect the new situation?

· Issue level

· All levels

· Group level

Actions are renamed at the group level to align them with the appropriate business context.

· Action level

A bank wants to leverage the Next-Best-Action capability of Pega Customer Decision Hub™ to promote new offers to each customer on their website. What information does Pega Customer Decision Hub send back to the website in response to the real-time container request?

· The treatment details and relevant action attributes

Pega Customer Decision Hub evaluates the actions from the associated issue/group and returns the resulting action details back to the website in the form of the image, description and other relevant attributes.

· Only the image location

· Only the image location and its type

· Only the action name and description

U+ Bank, a retail bank, does not want to annoy customers by offering them a mortgage refinance option if they have less than 5% to pay off on their loan, although it would be profitable for the bank. Which engagement policy condition best suits this requirement?

· Eligibility

· Suitability

· Applicability

· Suppress an action for 30 days if there are 3 impressions for any channel without a click.

· Suppress an action for 30 days if there are 3 rejects for web channel.

· Suppress a group of actions for 30 days if there are 3 impressions for the web channel without a click.

This rule definition suppresses a group of actions if 3 impressions are recorded in the web channel.

· Suppress a group of actions for 30 days if there are 3 rejects for any channel.

The arbitration factor that allows you to assign financial values to actions is called: _________________________.

· business levers

· context weighting

· action value

Action value allows the business to assign financial values to offers and prioritize high-value offers over low-value ones.

· propensity

U+ Bank has decided to nudge the Platinum Plus credit card to customers who visit their home page. Which arbitration factor do you configure to implement this requirement?

· Action value

· Business levers

Business levers allow the business to manually assert some level of control over the prioritization of offers.

· Context weighting

· Propensity

U+, a retail bank, has recently implemented a project in which credit card offers are presented to qualified customers when they log in to the web self-service portal. To show the offers per the bank’s requirements, the bank added all existing contact policy conditions. What is the immediate next step they should take?

· Go live for all customers and check the performance on a weekly basis.

· Conduct numerous what-if simulations before going live.

· Go live for a limited number of customers and check the performance on a daily basis.

· Add unit tests using persona testing before going live.

Once the bank adds all existing contact policy conditions, they need to conduct a unit test using persona testing as Personas are predefined per business requirements and all the tests should pass.

Pega Decisioning Consultant - Next-Best-Action in an omnichannel environment Module Quiz & Answers

2021-12-05T19:54:00.001+05:30

Pega Decisioning Consultant - Next-Best-Action in an omnichannel environment Module Quiz & Answers

If the Pega Customer Decision Hub presents Next-Best-Action recommendations to a customer in a call-center, the Next-Best-Action is re-evaluated when _______________, ___________, and ___________.(Choose Three)

· the service representative completes a task

When the service representative completes a task, the Next-Best-Action is re-evaluated.

· a customer changes the call context

The Next-Best-Action is re-evaluated by using the new call context because this is new information.

· the service representative is in the middle of completing a task

· a customer responds to an offer

When a customer responds to an offer, the response is saved, and a new Next-Best-Action is evaluated.

· the marketer retires an offer

In a call-center application that receives Next-Best-Actions from Pega Customer Decision Hub, the customer service representative (CSR) is _______________.

· always expected to sell a product or service irrespective of the customer's call intent

· expected to improvise based on some basic customer information displayed on screen

· forced to follow a strict path of recommended steps, from which the CSR cannot deviate

· guided on the next important conversation to have with the customer

Pega Customer Decision Hub guides the CSR by recommending Next-Best-Actions

PEGA Customer Decision Hub - One-to-one customer engagement - Module Quiz and Answers

2021-12-05T19:52:00.001+05:30

PEGA Customer Decision Hub - One-to-one customer engagement - Module Quiz and Answers

· The call center

In a call-center, a customer service representative can use Next-Best-Action recommendations to provide one-to-one customer engagement.

· SMS

SMS is a valid channel.

· A retail store

In a retail store, a customer service representative can use Next-Best-Action recommendations to provide one-to-one customer engagement.

· Billboard on the company building

· Traditional television advertisements

Which statement best describes the goal of Next-Best-Action?

· Ensure that the customer is always given a desirable offer.

· Balance customer needs with business objectives.

Next-Best-Action weighs customer needs against business objectives to optimize decisions based on priorities set by the business. This is the goal of Next-Best-Action.

· Ensure that every customer receives the same action.

· Provide insight into business processes.

Next-Best-Action ensures that communication between the business and the customer is__________ and __________. (Choose Two)

· free of jargon

· uniform and generic

· timely

The artificial intelligence embedded in the Next-Best-Action platform ensures that every message is relevant and timely, so the customer can take immediate action.

· contextual

The artificial intelligence embedded in the Next-Best-Action platform ensures that every message is relevant and contextual, so the customer is more likely to respond.

PEGA Simulation - Test and Learn Approach to Maximize the Marketing KPIs

2021-05-09T17:31:00.003+05:30

What is ‘test and learn’ marketing?

Test and learn marketing is a data-driven approach to constantly optimizing Strategies and to improve the KPIs performance of recommendations made from PEGA Decisioning Simulation capability through a series of ongoing tests. It allows organizations to convert insights into hypotheses and then test those theories to prove their value. Primarily to improve the take rate of recommendations made from PEGA OR it could be improving the revenue AND/OR margin for an Organization. It also could be a two different variant of the Treatment for the same action to the same channel. Eg. Having two variants of the Email treatments for the same Action. This is a perfect example of test and learn marketing.

Test: Taking the guesswork out of marketing

Test and learn principles remove this speculation by building a data-driven system that proves the success and failure of individual marketing strategies. Instead of relying on correlative insights, we can run the PEGA Simulation to attribute meaningful KPIs to each change, measure performance and test variations to determine which strategy is most effective.

Learn: Turn insights into better marketing decisions

The learn aspect can be as simple as finding out which hypotheses are correct and prioritizing them in order of value (which meets the Organisation KPIs objective already set). We can also learn from previous experiments (and their data) to create new hypotheses or determine which testing opportunities meeting the marketing KPIs.

We could also leverage an existing PEGA Decisioning Machine learning AI capabilities like Adaptive Modelling, Predictive Modelling to experiment to spot opportunities for testing, makes recommendations based on your results and predicts the outcome/value.

A good test and learn marketing principles has two main objectives:

Increase conversion rates through testing variations.
Learn from previous tests and apply findings to future marketing decisions.

We run a series of tests to determine the best outcome for specific scenarios and we collect all of this data to spot patterns and inform smarter marketing decisions.

By applying a test and learn model to all of our marketing campaigns, we can improve every aspect of brand performance with data-driven insights. The more tests you run and the more data we collect, the more reliable these insights become and the more robust our marketing decisions will be.

Some of the example of Goal for Test-and-Learn approach

Measure the Impact of Decisioning Framework values (Real Time Controls) changes and to align Organizational KPIs
Test the effectiveness of different treatments for the same Action for the same Channel Eg: Keep different Email Treatment (Title and/or content) for Control and Test to measure the impact
Determine which Treatment Content generate the highest engagement.
Test the potential value of a new Channel.
Calculate the lifetime customer value of leads based on acquisition channel and their position along your marketing funnel.
Identify negative friction that’s preventing leads from converting into customers.
Optimize marketing funnel to reduce dropouts and maximize conversions.
Optimize the customer experience to maximize repeat purchases and lifetime customer value.

A test and learn model can be applied to any marketing objective and campaign type where we want to maximize performance and collect insights to inform better marketing decisions in the future.

How to apply a test and learn model in PEGA Decisioning & Marketing

Some quick overview of the key steps to take in test and learn model are:

Define goal and KPIs: It’s crucial that Organisation should have a specific goal in mind and understand which KPIs truly measure success. It could be higher engagement reate, higher order rate, improving revenue, margin and reducing churn etc.
Develop hypothesis: This is the theory that your tests will prove or disprove – to achieve the same KPI, there could be different school of thoughts. Ideas will help us to develop hypothesis.
Create testing criteria: To get meaningful results from tests, weneed to define strict testing criteria and remove every possible variable that might skew the desired outcome.
Test ideas with the highest potential first: This will have the biggest impact on performance and collect the most valuable data early on – but it also ensures that our test and learn models achieve a positive ROI as soon as possible.
Run your tests until statistical significance: This ensures your results are reliable enough to inform decisions while mitigating for variables outside of your control.
Turn insights into action: Individual results help you make specific decisions but collecting data from all of your tests helps you to make informed predictions and decisions for future campaigns – for example, which ad format is most effective for your campaign message or how much to bid to achieve your target reach.
Measurable success post implementation: Once right Strategy has been identified, implement the hypothesis produced results closed to KPIs and make the BI tools in place to measure the success/failure of the recent change.
Apply Continuous Improvement Technique: By learning from successes and failures, we continue to do what works and constantly improve upon what doesn’t

This test and learn approach can be applied to any marketing strategy and, PEGA Customer Decision Hub Simulation capability would help to achieve the possibilities in a quick turn-around time.

Happy Learning!

Nanjundan Chinnasamy

PEGA Simulation - A Technique in the PEGA Marketing to test and Solve Problems in the Marketing KPIs

2021-05-08T16:15:00.003+05:30

Today i would like to give some insights on The Use of PEGA Simulation in Solving the Problems in Business/Marketing KPIs. This article focuses on utilization of analysis of different possibilities using a Simulation feature made available in PEGA Customer Decisioning Hub. For a given business problem, there will be more than one solution. Each solution is analyzed with the help of simulation. They have been evaluated and the optimal solution was selected.

The modern trend these days is to optimize everything that we can, especially in Marketing when PEGA Customer Decision Hub installed to drive the Marketing messages for an Enterprise. The result is the achievement of predetermined targets (KPIs), such as reducing Churn, Increase Revenue from Each customer, Increase Margin and increase the proposition value for each customer. Most of the Organizations are lagging in measuring & optimizing the Outcome of the Marketing messages against Organization KPIs. It is not all about recommending the ‘number’ of marketing messages at various customer touch points. Organizations could start exploring the ways to optimize the current logic and run the various simulation options to understand the Strategy which brings values close to the KPIs made available.

Let's discuss one of the Telecom business problems and understand how PEGA Simulation will help Markets to test and Learn to maximize the business outcome. Aka. KPI

Problem:

Let's consider three huge companies in the telecommunications market in the US. Each company sold some of the four products (known as “quadruple play” when combined), including high speed Internet, cable TV, telephone, and cell phone services. Many households purchased individual services from the different companies. The aggressiveness of the players made “product bundling” a key marketing strategy, but there was not a clear understanding of how to use this strategy, or the impact it might have on the market.

Company A wanted to enter the markets that they hadn’t covered yet OR they wanted to cross -sell other products, but each one knew that penetrating the competitor’s niche would force them to reply in the same manner.

The challenge was to build a Strategy (Including Product Price and Offer price etc.. ) that would allow the client to analyze several scenarios, taking into account the whole telecom market (with its 3 major players) and the “product bundling” effect.

Solution:

After doing enough market study, the Marketing Team of Telecom company Arrived prices and offers for each product bundle combination. Marketing team arrived at the conclusion of “quadruple play” buble cost could be either $200 OR $220. They are not sure which price point would help to benefit both the customer and Organization to maximize their value.

Organization A can leverage PEGA Simulation capability to understand the impact of business KPIs (Churn, Revenue and Margin) keeping the possible price combinations to determine the best pricing Strategy. Strategy which gives us closest KPI outcome can be selected for Implementation.

Outcome:

It was the high flexibility of using PEGA Simulation capability to build, measure and Learn possible what-if scenarios. Outcome of the Simulation result can be discussed with Marketers explaining various organization specific KPIs. Marketing team could make Informed Decisions based on the simulation results produced for each what-if variance.

Simulation is one great technique that allows us to have a reliable view of possibilities before getting into Production. So we have a simple way to test an infinite number of variants to solve the problem and for the actual implementation to choose the best possible solution to the situation.Simulations help to detect problems and complications that resulted in normal operation and save significant costs that we had to then spend on their removal. In practice it is impossible to try different alternatives, in terms of irreversible steps that are expensive.

Conclusion:

By using simulation experiments, we can obtain results for different alternatives. Team can share the informed choices to the Marketing team before taking Decision to implement any Marking Strategies. There is a detailed knowledge base article made available in PEGA for managing Simulation tests in Customer Decisioning Hub. More details can be found here https://community.pega.com/knowledgebase/articles/decision-management/85/managing-simulation-tests-pega-customer-decision-hub

Drive Marketing Growth with the help of Real-Time Speech Analytics combining Al powered PEGA Decisioning

2021-04-18T14:43:00.000+05:30

Creating a positive customer experience is the key to building a successful business. Knowing what customers want before they change their minds, or move on to your competitors, will help create a positive customer experience. Since you can't read their minds, the next best thing is using speech analytics to capture 100% of your customer conversations and combine the Speech Analytics in PEGA's Next Best Action Decisioning Engine.

Customer feedback gives us the ability to better understand our customers and their concerns, needs, and ideas. Speech analytics saves businesses time and delivers value through loyal customers, increased revenue, and decreased expenses. But in reality, combining Call center Real-Time speech Analytics with the PEGA Decisioning Engine is not a straightforward and easy process. With the recent Rega Acquisition of Qurious.io (for Al-Powered Speech Analytics), integration of Speech Analytics in a PEGA Decision making process would become easy (hoping to hear updates from PEGA world 2021 event on 04-May-2021).

Large Enterprises contact centers typically address multiple challenges and try to resolve them through a measurable improvement process. In simple words...

PEGA Speech Analytics + PEGA NLP+PEGA AI powered Decisioning = Solve many industry problems exist today

I strongly believe Speech Analytics with the power of AI powered Decisioning would solve many of UNCOVERED industry issues today. Here are the most common areas that require constant business improvement.

Improve agent performance and reduce churn

Speech analytics can listen to every call. By listening for keywords and phrases, ensuring the agent follows processes, and by analyzing both agents and customers language and tone for sentiment, every call can be automatically scored against multiple criteria. What's more, these rules will be applied perfectly consistently. As a result, you can improve overall performance with additional training to plug the skills and knowledge gaps identified. This also helps to improve the speed to competency for new recruits, and reduce chum in those all-important first few weeks and months.

Speech analytics can also help us to stay in touch with the emotional and mental well-being of our agents Tone and sentiment analysis is used to assess both parties in an interaction If an agent shows signs of stress, frustration, anger or other negative emotions, this will inevitably come through in the analysis Managers can then be warned to intervene with a metaphorical arm around the shoulder. additional training, or even counselling.

Gain insights into customers and competitors

Even if we are already recording all calls and listening in to a small percentage of them for compliance and training purposes, that still means that most of the useful information in those interactions is not being taken on board.

While talking to our agents, our customers give up lots of incredibly detailed information in off-the-cuff comments related to such things as how they use our products, how our prices compare, how accessible and efficient our after-sales care is, and most importantly how we stack up against your direct competition. This is gold dust insight that you would normally need to conduct thousands of surveys to uncover and it's right there already on a dusty server in your unlistened to call recordings.

Sales and marketing teams can leverage this information with the help of modern technologies and use it to inform their decisions on everything from product development to pricing, to market positioning and what sales channels to use.

Generate more sales

Real-Time Speech analytics combined with Decisioning allows us to identify what sentiments in what situations lead to what behaviors and what the results usually are.

We can then redesign processes to eliminate behaviors that don't lead to sales and retention, and encourage ones that do Decisioning logic to take advantage of the best moments during interactions to make an upsell or cross-sell offer, ensuring that closing rates are maximized Outbound contact.

programmers can also be used to follow up with customers who had, for whom the analytics predict are likely to have a negative experience with a product or service.

Predict and understand your metrics and improve them

Using speech analytics, we can take the measure of each customer's tone of voice and words used to actually predict- quite accurately the customer satisfaction or NPS rating the customer would have given for a particular call This means that rather than relying on the few customers we do follow up with to arrive at those scores, we can effectively get a predicted satisfaction rating for every interaction.

Linguistic analysis can also pick out customers' verbatim comments made to agents to help us understand exactly what they do and do not like about our products, service levels, and processes Feed this information into our analysis of our metrics when you collect them to understand why customers give the scores they do, and what they would like us to do to improve them.

Prevent Customer fraud

Customers may be "king" but that doesn't mean they always do the right thing Speech analytics can not only identify but predict the likelihood of customer fraud with the help of Al Using the outputs of speech analytics (transcriptions, interaction analytics etc), a supervised machine learning module was built against a training data set ("Yes Fraud" and "No Non-Fraud calls). After blind tests and ongoing improvements, the supervised learning model has been operationalized as a customer voice data feed to the existing Fraud Risk engine. Customers are now triaged based on enhanced risk prediction to our Marketing Decisioning Engine

Turning Insights into Actionable Results

Speech analytics can undoubtedly provide its users with a wealth of agent, customer and contact center related information. However, the real trick lies in finding the most relevant insights from the pool of agent-customer interaction data. These insights can then be used to attain the required results and keep the contact center's operations away from any trouble Speech Analytics Insights are "Gold Digger" for business team and use them to make actionable results in both inbound and rest of the customer touch points including outbound channels.

Understanding the Factors Causing Call Dispositioning

Commonly used to describe the outcome or final output of a particular call, call disposition codes or labels are used by agents to classify calls under different heads such as miscellaneous, need follow-up, left voicemail and others Agents can attach such tags to these calls due to several reasons such as impractical call, need monitoring by the agent, saving time and others.

With speech analytics, it gets easier to classify the available call data under different heads so that it gets easier to attain the desired results. It would also get easier to know the reason behind a particular call, gain relevant business insights, etc.

Identify and correct processes or automation outliers

Organizations can use speech analytics to find terms associated with specific processes. Organizations can use Speech Analytics to understand the workflow/Processes broken/requires betterment to improve customer experience.

Fulfillment of an order
Refunds or returns
Employee automation Missing items
Broken systems

Average handle time (AHT) reduction

Understanding long calls also helps identify what customers really want and what the pain points in our product, services are and uncover the potentials to improve both Agent and customer experience.

Resolving customer issues on the first call (Improve first contact resolution)

First call resolution, also known as first contact resolution or FCR, is a company's ability to handle a customer's call, email, question, or complaint during their first outreach for that specific incident. With the help of Speech Analytics in a Decision making process will help us to resolve customer issues on the first call.

What do you think? Do you think we can solve other usecases? Please share in comments section.

Happy Learning,

Nanjundan Chinnasamy

Al Powered Real-Time Speech Analytics in PEGA Decisioning & Marketing My expectation for PEGAWorld 2021

2021-04-17T10:49:00.003+05:30

With the recent Pega Acquisition Qurious io (for Al-Powered Speech Analytics), the dynamics of Call Center solution in CRM would be changed in coming days Both Inbound & outbound service calls can be analyzed in real time. Qurious io's speech to text conversion capabilities, Natural Language Processing (NLP), and emotion detection capabilities to analyze the dialog within each customer service call real-time insights can be feed to PEGA's Centralized Decisioning Brain to improve customer interactions, make better recommendations, and boost customer loyalty and sales. I am expecting a major announcement on this topic in PEGAWorld 2021 planned on 04-May-2021.

Major clients adopted PEGA CDH solution as Marketing tool and exposed their Decisioning logic as a Service to integrate with Organizations Proprietary legacy complex call center software to service customers. There is an Increasing demand for combining Real Time speech Analysis In-sight with PEGA's Decisioning Engine to solve many known business problems exist today in Call-Center application Call Center is a very good channel to connect with customers, understanding the feedback for our products and services and most importantly the customer concerns, emotions and feedback (both verbal and non-verbal sentiments) etc.

Improve Strategic Business Decisions

Improve strategic decisions basis sentiment and conversation insights to understand your customers better to refine your future serviceability and product offerings

Manage Operations Efficiency

Basis the conversation analytics reports analyze your team's performance in handling the conversations and design future training courses for Call Center Agents. The outcome will be smooth chent handling benefits while offering improved Customer Experience.

Accuracy

Make more sense of transcription with domain specific targeted words/phrases likes addresses, currencies, years, abbreviations etc.

Couple of Call Center usecases we can solve with the help of Al Powered Real-Time Speech Analytics in PEGA Decisioning & Marketing Contact center solution to improve the customer experience by providing real-time update about the offers, services.

Keyword Spotting:

Focus & identify specific Keywords and parses to filter only the relevant conversations derive domain specific insights & performance Speech Analytics keyword can be used in Decisioning Engine to pitch Sales/Service specific messages in Real-time.

Theme Discovery

Identity the Intent & purpose of the conversation to take proactive actions and manage them better.

Customer Segment Identification

Create & identify the new customer segments based on their conversations to enhance the personalized experience.

Root Cause Analysis

Once PEGA NLP categorized the calls using Real-Time Speech Analytics, PEGA Decisioning capability can be utilized to make Product recommendations. Result of the Decisioning outcome can be used to device the root cause combining NLP results. It will help us to find out what you do not know to look for.

Reps' Conversation Analysis

Analyze Reps conversational etiquette like talk to listen Ratio and speech ratio to plan the Rep's personalized training Analyze every conversation and identity the trends or insights per Agent/Employee.

Real Time Alerts

Trigger Real-Time notification on the occurrence of custom words or events important to an Organization. Primarily to Save the customers when the customer identified as High-Risk customers and the likelihood of churning is High.

Soon I will be publishing detailed usecases and the benefits organization can unlock with the help of Speech Analytics in PEGA Decisioning. Stay tuned!

Happy Learning,

Nanjundan Chinnasamy

Enhance Your Personalized Messages to Customer using External Data Feeds/Public data

2021-04-06T18:28:00.000+05:30

Mostly Organizations are using their own Customer Analytical Records (All the information about a Customer data, products, usage and Marketing data) as part of Decisioning process whether its Inbound channel Real-Time request or Proactive outbound communication to send the personalized marketing message using tools like PEGA CDH, Adobe, SAS, Unica etc.

Personalization has become a must-have for messaging because of high customer expectations. To take Marketing personalization to next level, integration of external data feeds/publicly known information about the customer as part of Decision making process is inevitable.

I would like share few use cases which can enhance personalized messages to Customer in the Communications and Banking industries.

External Data Feed#1: Integrate Official Emergency services & weather alert systems API data to PEGA Decisioning engine

Using weather alert system data & joining the same with Organizations own proprietary Customer Analytical Records will help Organizations to target the Customers affected by bad weather/ natural disaster. (Post code can be used to identify the customers impacted to send hyper personalized marketing message). External data source will help Organization to prioritize the Nurture/Service messages to the Customers over Sales message.

Corporates can also use the publicly available weather alert systems API Data & send proactive service/alerting messages. Timely, relevant and Empathetic message will help Organization to increase customer Life Time Value and NPS.

Sample use cases to use the External source data to send hyper personalized Marketing message:

When customer postcode matches with natural disaster affected postcode:

o For Banking & Communication, Waive-off late fee & allow them to pay the bit later

o For Communication, Make some additional data & call free offer for affected customers until the situation is restored

o For Communication, Send proactive service outage messages & notify the team who are managing the Infrastructure/Towers about the event.

o For Banking & Communication, Prioritize the Nurture messages over sales (send proactive service outage message with ETA to restore the service)

o For Travel, send a message with weather information for an upcoming trip

o For Retail, send users a list of products that they might be interested in based on the current location (if its affected by Bad weather)

External Data Feed#2: Integrate Foreign Exchange API data to PEGA Decisioning engine

For the customers who are buying the ForEx regularly OR the Customers who are setup the Standing order to other Country, proactive personalized offer when there is a significant change to the ForEx will help Customers to book the ForEx in advance. Hyper personalized Marketing message will help Banks to increase their ForEx sales and Customers would happy with the Exchange Rate deal they received.

To talk specific to PEGA Decisioning, mostly the prioritization of the offers/Actions is combination of ADM Propensity, Context Lever, Offer Value, Business Lever etc. Managing Offer value, Business is done by the Marketing Department most of the time through Revision Management process AND/OR other well defined Rapid deployment feature. Majority of the time, the opportunity will be lost before marketing team reacting to get the Marketing lever changes validated and implemented in Production. Very few Organizations doing Rapid deployment in 2 days’ time, few are doing Revision Management deployment in 2 weeks and majority of them deploying Marketing lever changes in 3-4 weeks’ time (BAU release change release).

Integration of External source data source could also help us to override Marketing levers to specific Target Group (Customers affected by bad weather in my previous example) and also it will help us achieve automated data-driven decisions from PEGA in real-time. This will eliminate of manual lever changes to force the specific/group of propositions to the customers who are in-need.

What are the other use cases you can think about to make the hyper personalized marketing messages by integrating External data as part of Marketing Decisioning process? Please share those in comments section.

Happy Learning,

Nanjundan Chinnasamy

How does PEGA Marketing/Decisioning Strategy work? Understanding the PEGA Marketing/Decisioning Strategy execution through “Marketing funnel”

2021-03-21T13:12:00.000+05:30

I have come across the scenarios where Marking team is finding difficulties in understanding how does PEGA Marketing/Decisioning Strategy work. As a technical guy, I found bit difficult in explaining the PEGA’s complex Decisioning Strategy logic in non-technical terms where all Markers can understand the complex logic.

I would like to explain the PEGA Strategy logic with the “Marketing Funnel”. Yes, PEGA Strategy rules filters the offers using Marketing Funnel technique. All The eligible offers will send over to the top level strategy and each strategy has logic to filter the offers (applying rules) similar to the Marketing funnel. PEGA Strategy has many pre-built Strategy components & uses the same to select offers and send to next stage.

A Marketing funnel is a way for us to track the Offer eligibility of customers. By understanding where in the funnel, or where in the customer’s eligibility, Marketers can decide what kind of marketing message to send them.

The marketing funnel is simply a visual representation of a sometimes difficult subject to visualize. Think of it as a map of your businesses marketing and sales processes, procedures and strategies. Left of the funnel includes your broadest marketing efforts and is narrowed as potential Offers move through it. The breadth the funnel goes the more focused your potential Offers become. Eventually you will weed out all the Offers that are not willing to recommendations and left with the most valuable sales qualified Offers.

Marketing funnels are so effective is because it makes you take a hard look at exactly how our business recommendations various offers based on the context. What eligibility criteria to adjust to recommended the offer to balance customer needs & business objective.

Defining Engagement Policies:

Defining Engagement policies in PEGA7 done by when rules & set of PropositionFilter. All the criteria's are classified as Eligibility/Hard rules.

Defining Engagement policies in PEGA8 simplified with NBA Designer. PEGA8 NBA Designer uses E(Eligibility), A(Applicability) and S(Suitability)– Rules by clearly separating engagements.

Eligibility rules, which are strict rules representing what it is possible to offer.
Applicability rules, which represent business practices that limit what to offer based on a customer’s current situation. These are not as strict as eligibility rules.
Suitability rules, which represent what the business should and should not do ethically and empathetically. These are the least strict rules.

Pega Decision Management combines business rules (Engagement policies- specify the conditions under which an offer or group of Offers is available for a customer), predictive and adaptive analytics with real-time Decisioning to initiate and adjust processes based on the business criteria we have established. Inbuilt PEGA Decisioning rules help us to select the right offer ensuring the right decision for the right customer at the right time.

Pega Decision Management makes defining complex decision strategies simple and efficient to help organizations:

Dramatically improve customer experience in every channel with strategies based on real-time, actionable insight into operational and behavioral data.
Rapidly deploy intelligent processes with pre-built business accelerators to create and maintain comprehensive decision strategies without the need for any coding.
Make dynamic changes to decisions, processes and interactions based on real-time customer data and feedback.
Leverage adaptive and predictive capabilities to make the best possible decisions based on historical and real-time responses.
Seamlessly integrate existing applications and processes to improve operational efficiencies and respond to customers across all channels.

Simplifying Fulfillment process from PEGA Decisioning/Marketing recommendations

2021-02-28T13:09:00.001+05:30

Most of the times recommending the offer from PEGA as part of the Decision making process and Acceptance rate is being considered as a SUCCESS of Marketing campaign. As a Marketing Manager, I would like to see the overall success by measuring the Impressions, Acceptance and the Orders completed following an existing fulfillment process.

Let’s look at the sample Decisioning response with various scenarios used to achieve this.

Option#1 (Populate CallToAction link for each Proposition response to redirect the Sales Landing Page)

Let’s look at the following PEGA Decisioning response for one of the sales scenario. You could see only CustomerID and List of Top X propositions recommended from the PEGA Decisioning Engine. Click of the CallToAction link would be considered as SUCCESSS. This might be TRUE for all the informational/Nurture propositions. Do you think the same solution would work for Sales Proposition where the Order fulfillment needed? I don’t think so.

PEGA RESPONSE:

Sample Self Service channel application screen post Clicking the CallToAction Landing Page:

We can clearly see that both Customer Information & Proposition information is not pre-populated. Customer has to key all the mandatory input to full-fill the application process & regular eligibility check has to done even though the system has most of the required data to complete the fulfillment process.

Option#2 (Populate CallToAction link for each Proposition response + Proposition specific payload and redirect the Sales Landing Page)

Let’s look at the following PEGA Decisioning response for another sales scenario. You could see only CustomerID and List of Top X propositions recommended from the PEGA Decisioning Engine. One Difference here is Proposition contains all the Payload information required to complete the fulfillment process. Along with CallToActionLink, payload information required to fulfill the order also being supplied.

<DecisionResponse>
       <CustomerID>CE-1</CustomerID>
       <InteractionID>641889359827003657</InteractionID>
       <PropositionPropositionResults>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>Banner1</Name>
                     <Rank>1</Rank>
                     <CallToAction>http://abcbank.com/CCLandingPage</CallToAction>
                     <PropositionPayLoad>
                           <AccountPayLoad>
                                  <AccountGroup>CreditCard</AccountGroup>
                                  <AccountType>Classic</AccountType>
                                  <PreApprovedLimit>800</PreApprovedLimit>
                           </AccountPayLoad>
                           <AppointmentPayLoad>
                                  <BranchCode></BranchCode>
                           </AppointmentPayLoad>
                     </PropositionPayLoad>
              </PropositionResult>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>Banner2</Name>
                     <Rank>2</Rank>
                     <CallToAction>http://abcbank.com/CurrentAccountLandingPage</CallToAction>
              </PropositionResult>
       </PropositionPropositionResults>
</DecisionResponse>

Sample Self Service channel application screen post Clicking the CallToAction Landing Page:

We can clearly see that only Proposition information is pre-populated based on the decision made earlier. Customer has to key all the mandatory input to full-fill the application process & regular eligibility check has to done even though the system has most of the required data to complete the fulfillment process.

PEGA Decision Engine owns most of the customer data as part of Customer Analytical Records. Can't we use the same to pre-populate the application form to make the fulfillment easier? Yes, this brings the option#3

Option#3 (Populate CallToAction link for each Proposition response +Customer Information + Proposition specific payload and redirect the Sales Landing Page)

PEGA can play a major role to simplify the fulfillment process by passing all the required payload information (Customer Data and OfferData) to make the fulfillment process easy and smooth.

<DecisionResponse>
       <CustomerInfo>
              <CustomerID>CE-1</CustomerID>
              <FirstName>ABC</FirstName>
              <FirstName>XYZ</FirstName>
              <AddressLine1></AddressLine1>
              <AddressLine2></AddressLine2>
              <AddressLine3></AddressLine3>
              <AddressCity></AddressCity>
              <AddressCountry></AddressCountry>
              <AddressPostcode></AddressPostcode>
              <Email>abc@gmail.com</Email>
              <MobileNo>XXXXXX3923</MobileNo>
              <DOB>01/01/1970</DOB>
       </CustomerInfo>
       <InteractionID>641889359827003657</InteractionID>
       <PropositionPropositionResults>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>Banner1</Name>
                     <Rank>1</Rank>
                     <CallToAction>http://abcbank.com/CCLandingPage</CallToAction>
                     <PropositionPayLoad>
                           <AccountPayLoad>
                                  <AccountGroup>CreditCard</AccountGroup>
                                  <AccountType>Classic</AccountType>
                                  <PreApprovedLimit>800</PreApprovedLimit>
                           </AccountPayLoad>
                           <AppointmentPayLoad>
                                  <BranchCode></BranchCode>
                           </AppointmentPayLoad>
                     </PropositionPayLoad>
              </PropositionResult>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>Banner2</Name>
                     <Rank>2</Rank>
                     <CallToAction>http://abcbank.com/CurrentAccountLandingPage</CallToAction>
              </PropositionResult>
       </PropositionPropositionResults>
</DecisionResponse>

Sample Self Service channel application screen post Clicking the CallToAction Landing Page:

We can clearly see that both Customer and Proposition information is pre-populated based on the decision made earlier. Customer can validate (make the amendment if needed to key all the mandatory input) and complete the application process.

Option#4 (Making PEGA Response API Generic to populate the fulfillment process to all types of Landing Pages)

Option#3 sounds interesting right? If PEGA passes the required customer & sales payload, the fulfillment process would be easy! There is a design constraint here. The payload information required to complete the loan account is different from Creditcard. If post started sending additional proposition like appointment booking decision rom PEGA, the payload structure will be completely different from Sales proposition. Considering there is PEGA Decisioning HUB & the logic is exposed as a Headless Decision. We would be having only one Decisioning API to manage the Decisioning requests across the channel and propositions.

The complexity comes when having one headless PEGA Decisioning API to manage the different Sales Propositions passing the payload from PEGA. To manage this API response payload complexity, PEGA could send the Proposition/Action specific payload in a generic response using xml CDATA option.

What is XML CDATA?
CDATA is defined as blocks of text that are not parsed by the parser, but are otherwise recognized as markup.

<![CDATA[ <message> CDATA test message </message> ]] >

Characters between these two enclosures are interpreted as characters, and not as markup. This section may contain markup characters (<, >, and &), but they are ignored by the XML processor.

How to Apply CDATA feature to manage the fulfillment need for dynamic payload from PEGA response?

Let’s look at the Payload being populated for Proposition#1. PropositionPayLoad is the generic tag used to populate the Payload. It’s not bound to any proposition contract. PropositionPayLoad is populated with the payload required for CreditCard Limit increase offer.

<DecisionResponse>
       <CustomerInfo>
              <CustomerID>CE-1</CustomerID>
              <FirstName>ABC</FirstName>
              <FirstName>XYZ</FirstName>
              <AddressLine1></AddressLine1>
              <AddressLine2></AddressLine2>
              <AddressLine3></AddressLine3>
              <AddressCity></AddressCity>
              <AddressCountry></AddressCountry>
              <AddressPostcode></AddressPostcode>
              <Email>abc@gmail.com</Email>
              <MobileNo>XXXXXX3923</MobileNo>
              <DOB>01/01/1970</DOB>
       </CustomerInfo>
       <InteractionID>641889359827003657</InteractionID>
       <PropositionPropositionResults>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>Banner1</Name>
                     <Rank>1</Rank>
                     <CallToAction>http://abcbank.com/CCLandingPage</CallToAction>
                     <PropositionPayLoad>
                           <![CDATA[
                                  <AccountPayLoad>
                                         <AccountGroup>CreditCard</AccountGroup>
                                         <AccountType>Classic</AccountType>
                                         <PreApprovedLimit>800</PreApprovedLimit>
                                  </AccountPayLoad>
                           ]]>
                     </PropositionPayLoad>
              </PropositionResult>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>Banner2</Name>
                     <Rank>2</Rank>
                     <CallToAction>http://abcbank.com/CurrentAccountLandingPage</CallToAction>
              </PropositionResult>
       </PropositionPropositionResults>
</DecisionResponse>

Let’s look at the Payload being populated for Proposition#1 for a scenario. PropositionPayLoad is the generic tag used to populate the Payload. It’s not bound to any proposition contract. PropositionPayLoad is populated with the payload required for Appointment booking offer.

<DecisionResponse>
       <CustomerInfo>
              <CustomerID>CE-1</CustomerID>
              <FirstName>ABC</FirstName>
              <FirstName>XYZ</FirstName>
              <AddressLine1></AddressLine1>
              <AddressLine2></AddressLine2>
              <AddressLine3></AddressLine3>
              <AddressCity></AddressCity>
              <AddressCountry></AddressCountry>
              <AddressPostcode></AddressPostcode>
              <Email>abc@gmail.com</Email>
              <MobileNo>XXXXXX3923</MobileNo>
              <DOB>01/01/1970</DOB>
       </CustomerInfo>
       <InteractionID>641889359827003657</InteractionID>
       <PropositionPropositionResults>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>ApptmentBooking</Name>
                     <Rank>1</Rank>
                     <CallToAction>http://abcbank.com/AppointmentBookingPage</CallToAction>
                     <PropositionPayLoad>
                           <![CDATA[
                                  <AppointmentPayLoad>
                                  <BranchCode></BranchCode>
                                  </AppointmentPayLoad>
                           ]]>
                     </PropositionPayLoad>
              </PropositionResult>
              <PropositionResult>
                     <Issue>Banners</Issue>
                     <Group>Sales</Group>
                     <Name>Banner2</Name>
                     <Rank>2</Rank>
                     <CallToAction>http://abcbank.com/CurrentAccountLandingPage</CallToAction>
              </PropositionResult>
       </PropositionPropositionResults>
</DecisionResponse>

What do you think? Do you think using CDATA in a xml response help us to manage & decouple the payload contact to ease the fulfillment process from PEGA response? Feedback appreciated. This solution can also address the Data quality issue being introduced to the system.

Mitigate the Data Quality Issue:

Pre-populated the customer data from System Of Record along with payload information would prevent the data quality issue. Managing the single source of Truth information about the customer is very critical to any organization to deliver the Decisioning & Marketing actions timely & contextual manner.

Simplify the Order Fulfillment Experience:

In order to drive Upsell/cross sell new products to the customers, you have to make the fulfillment process easy and exciting for people to order again. If most of the customer and proposition information pre-populated, fulfillment process could be done with very few clicks. It would create memorable experience for the customers & it would stand out from other competitors

Conclusion:

As part of PEGA Decision making process, PEGA could send the payload information needed to make the Order fulfillment process for both Inbound & outbound channels. Its all about the making customer journey smooth & easier from Decisioning->Impression->Acceptance->Orderfulfillment.

Happy Learning,

Nanjundan Chinnasamy | PEGA Lead Decicioning Architect

PEGA CDH & Digital Transformation – The need of focus towards Decisioning & Marketing daily Operations

2021-02-21T14:41:00.004+05:30

The adoption of data analytics is one of the greatest drivers of digital transformation, as businesses seek greater data-driven insights. Customer Analytical Records (Customer360 OR CARs) Data acts as a source of truth that helps teams focus on the critical factors that determine business resilience. Businesses are acutely aware that they must become more resilient by using technology especially with PEGA where PEGA CDH adopted as Brain for Centralized Decision Hub to recommend Next Best Actions/Offers/Contents/etc.

Companies are using daily customer data & real-time data to their advantage to advance their operations, enhancing the applications, and closing the loop by feeding key business applications. This helps to enable optimization of the cost, Investment, enhanced analytics, and modeling/simulation – and this ultimately means improvements in business efficiency across the entire operations.

This has been particularly true for the enterprises, where data has had a significant impact in five key areas:

§ Real-time operational information is increasingly being used to understand what is happening in real-time and enables the condition management of Marketing and operations lifecycles. For example, a dashboard displaying the acceptance/Rejections and fulfillment of the offers in real-time understanding of the Marketing Operational behavior and state. It will help us to quickly react to the change introduced to the system when a new Marketing Offer. Tools like ELK stack can be integrated with the PEGA Decisioning flow to visualize the offers & its performance in Real-Time to understand the Real-Time Operational Information.

§ Historical operational information form Interaction History Table helps organizations to understand what has happened in the past to create intelligence around operational behavior of Marketing Offers. Through operational trends, display of KPIs and dashboards, you can create abstracted views of operational states. For example, a graph may be displayed on a dashboard showing the Marketing offer Accepted/Rejects majority of the time. This can be compared to the real-time Offer Acceptance, creating intelligence on the Marketing Offers long-term operational trends.

§ Simulation & Predictive analytics is used for what-if type modeling. Integrating real-time and historical data enables your team to assess potential outcomes of operational states and behaviors, even accounting for tertiary variables. Deterministic or non-deterministic models can then be applied for open-loop simulation and predictive analytics. For example, you can now estimate how many customers might accept/Reject the newly launched offer. Other Marketing ControlParameters can be tweaked & run the Simulation including Predictive analytics to forecast the Accept rate for various Control Parameter combinations.

§ Prescriptive analytics describes what’s needed to optimize Marketing Offer and operations lifecycles. Scenario-based guidance is created and delivered through learning elements and closed-loop algorithms to enable your team to calibrate planning and scheduling across the entire enterprise value chain. For example, using a unified Marketing model, scenario-based calculations can be used to optimize maintenance schedules and performance, minimizing impact to your operations.

§ Enhanced Marketing Investment achieved through a combination of real-time Marketing Operations Monitoring, reacting the data quickly through Rapid deployment process and forecasting the Impact of the Marketing Offer Acceptance will help organizations to make better Marketing Investment.

Be bold, reflect and evolve

Businesses require intelligent Marketing software like PEGA CDH along with additional Real-time Offer performance monitoring tool like ELK stack (if applicable) to address Marking pain points for value creation, productivity improvement, insight discovery, risk management, and cost optimization. With the right technology, businesses can be incredibly agile to manage costs, boost efficiency and avoid costly mistakes. The combination of digitization, automation and data driven insights, with a focus on sustainable business can be a key differentiator and a propelling force to help ensure businesses meet their goals of today and tomorrow.

Happy Learning!

Nanjundan Chinnasamy | PEGA Lead Decisioning Architect

Tracking effectiveness of the PEGA Marketing Campaign & real-time Decisioning response through UTM Parameters with CallToAction URL

2021-02-20T13:37:00.002+05:30

Often enterprises having difficulties in understanding the campaign drives the maximum traffic and business to their website. Since many large scale enterprises started moving towards PEGA Centralized Decisioning Hub (Unified Marketing tool to send hyper personalized contextual, timely marketing message to the customer) to serve the marketing message, it is most important & critical for them to analyze & measure the RoI for the investments they have made.

One easy way to measure & track the effectiveness of the Marketing message sent to from PEGA for both Inbound & outbound channels is using UTM parameters to their CallToAction link.

UTM parameters come into play to analyze & measure the marketing campaign that drives maximum traffic. Organizations can plan their investment based on the historical performance in a Omni Channel Marketing environment.

By tagging your URLs with UTMs (Urchin Tracking Module), you can understand how your visitors interact with your website/app/outbound campaign like SMS/Email.

Here’s how these UTM parameters appear at the end of your URL:

https://www.jio.com/recharge_singleclick?

planId=1008395&utm_source=NE&utm_medium=SMS&utm_campaign=Plan_expiry

Adding UTM parameters in all the CallToAction link provide extremely valuable insights from Analytics perspective to measure the effectiveness of the Offer & RoI . You can uncover a goldmine of behavioral data to help boost our sales and refine your overall marketing strategy (Offers, Channels etc).
x

What Are UTM parameters?

Here’s a succinct and super helpful definition from Kissmetrics:

“UTM parameters are simply tags that you add to a URL. When someone clicks on a URL with UTM parameters, those tags are sent back to your Google Analytics for tracking.”

As a PEGA Decisioning Consultant can plan & keep all the UTM parameters in a proposition catalog & finally build the CallToAction target link from proposition metadata.

There are five UTM parameters that you can attach to your links:

UTM source: Encapsulates the traffic source that in most of the cases is the platform on which you shared the link, for example, Google, LinkedIn, Twitter and Gmail.

UTM medium: Includes the marketing medium that is closely related to the source. For instance, if you use Google as a source, PEGACDH, Adwords etc.

UTM campaign: Underlines the campaign that you used to share the URL. You can name the campaign as you like, for example, “PlanExpiry“ for outbound campaign and “Inbound” for real time inbound call to offer recommendations from PEGA Decisioning engine.

UTM term: In most cases, this parameter is used for advertising and seizes the term you bid on for sharing your URL. For example, you might bid on the term “Drip Marketing,” and consequently, “drip marketing” will be the UTM term.

UTM content: A parameter that is used to determine the content that collected interaction when multiple elements from your ad promotion led to the click. This is especially useful if you A/B test more versions of your content.

Only UTM parameters are sufficient to measure the PEGA Decisioning performance?

NO. We can add as many custom parameters to track the marketing effectiveness (URL can have max 255 chars including params. We could add only relevant url parameters to measure the effectiveness).

Below is on the example where the CallToAction link contains the InteractionID (URL param is IxID), OfferName(URL Param O), ContentID (CONID)

https://www.pega.com/webinars/customer-engagement-series?IxID=-1055117343767813309&O=CXUnified_InsNOutsOf11Engagement_NBA500_ES1_EM181438&utm_source=LMMS&utm_medium=email&utm_campaign=Engagement_NBA&utm_content=20DE_CE_NA-NA_EM%28EM-181438%29_EM1_CI_OT_NBACDHWBSERIESREPLAYVIDEO_NA&CONID=CON-8314620

Why UTM Parameters Matter for PEGA Decisioning CallToAction Links?

By using UTM parameters we can gauge the types of marketing messages/offers that work and provide us with the insight needed for the ones that didn’t. Basically, there are 5 major benefits from using UTM parameters for your campaigns:

Cross-Channel Tracking: You’ve just created a dedicated landing page Or Offer message to the Market. How to measure RoI for this? What if 99% of your traffic comes from Inbound Web channel and only 1% from SMS campaign? With UTM parameters, you’ll know exactly which channel brings you long-term profits.

Improving Your Channel Campaigns: When you track the channel’s ROI and monitor the campaign’s impact, you’ll have a clearer picture of what provides you with the best outcome. Now, you’ll be able to focus on improving the channel’s impact.

A/B Testing: If you want to test two different CTAs because they both lead to the same link, you can use a UTM parameter. You can compare the engagement for both of your CTAs and determine where your target customers respond better.

Influencer Marketing: When you pay a social media influencer to market your product, you want to know if he/she really gets clicked on or it’s just a person with a fake followers count. Creating a custom URL with UTM tags can help you track their ROI efforts.

Finally,
Adding UTM parameters in all the CallToAction link provide extremely valuable insights from Analytics perspective to measure the effectiveness of the Offer & RoI . You can uncover a goldmine of behavioral data to help boost our sales and refine your overall marketing strategy (Offers, Channels etc).

Happy Learning!
Nanjundan Chinnasamy | PEGA Lead Decisioning Architect

Moving PEGA Adaptive Model learning between environments

2020-11-23T09:35:00.004+05:30

There might be a use case, we may need to copy/move the ADM learning from PRODUCTION environment to other lower environments to simulate the results OR Reproduce Some scenarios referring to ADM learning from Production environment.

The following steps should be sufficient to import learning to a target system even if that system has previously had ADM models itself. However, they assume that you want to completely replace any ADM data on that target system with data from the source system, not merge the two. It is also assumed that your Cassandra cluster is not set up for Active/Active, across multiple datacenters.

In the source system

1. Export the pyADMFactory dataset from the source System.

In the Target system

1. Ensure the adaptive rules are present.

2. Decommission all ADM nodes.

3. Navigate to the pyADMFactory dataset and run truncate operation.

4. If the target system has any model reporting data in the following tables, these should also be manually truncated to prevent misleading reports.

a. pr_data_dm_admmart_mdl_fact

b. pr_data_dm_admmart_pred_fact

c. pr_data_dm_admmart_pred (this may not exist depending on the version of Pega)

5. Connect to Cassandra on one of the DSS nodes

a. Remove the ADM model’s response lifecycle event data

drop keyspace adm_commit_log.

b. Remove the rest of the ADM Data

drop keyspace_null_adm and/or drop keyspace adm - which ever present

6. Navigate to the pyADMFactory data set and run the import data using the data exported from the source system.

7. Decommission ADM nodes (the first node to start will create scoring models from the imported factory data).w

8. When the ADM nodes have status NORMAL, check the Adaptive Model Management landing page. Model data should now reflect what was imported

PEGA Decisioning - Decision Table to be defined on the Strategy Result (SR class) or a Customer class? How to Deciside?

2020-10-31T13:24:00.003+05:30

One common design question usually asked by many of our Decisioning Architects is, where should i define my Decision Table? Whether the Decision Table to be defined on the Strategy Result (SR class) or a Customer class? How to choose the Applies to Class while creating my Decision Table in my Decisioning application.

The Decision Table can be defined on the Strategy Result, SR class, or a Customer class. The choice often depends on where the properties used in the Decision Table are located. Let us discuss the following three design options:

If the Decision table is using the properties from the Customer Class and Decision Table returns result from Decision Table OR result of the Decision Table directly sets the property available in the same customer class, you should create Decision Table in a Customer class.

If the Decision table is using the properties from the Customer Class, if you want to refer the very few computed properties from SR class, creating Decision Table in Customer Class OR SR class OR both options are valid. The design decision here could be, if you want to set result of the Decision Table to a specific property directly from the Decision Table. If you want to set the result of DecisionTable to a SR class, Create the Decision Table in SR class. If we want to set the result of DecisionTable to a Customer class, Create the Decision Table in Customer class. If the Decision Table returns the result and result of the Decision table referred using pxSegment result property, creating DecisionTable in Customer,SR class both valid.

Let us take an example below. Customer CreditScore is a derived property from SR class. OutstandingLoanAmount is a Customer class property. Based on these two property values, Decision Table returns RiskScore.

Decision Table to compute the RiskScore

Creating the table requires two condition columns. First is the Principal Loan, which is the property in the data model representing the outstanding loan amount.

The Operator represents the condition applied to the column. In this case, greater than, which allows you to express the Outstanding loan amount condition from the requirement.

The second condition column is the Credit Score property. The Credit Score is a parameter, so you need to use the Param.PropertyName construct.

The Use Range checkbox groups the credit scores together.

Fill in the bank’s requirements and specify a Return value for each row in the table.

Filter credit cards based on the calculated risk segment

Configure two Filter components to ensure that you identify High Risk and Low Risk customers.

Based on the Customers in the risk category, we can compute the customers eligiblity. The pxSegment Strategy property contains the output of the Decision Table.

Still confused with the Desion option to Define the Decision Table in a PEGA Decisioning application? Feel free to reachout to me.

Happy Learning,

Nanjundan Chinnasamy

PEGA Decisioning - Managing the Business Rules(Revision Management) for quick Production deployment

2020-10-11T00:19:00.004+05:30

PEGA Decisioning - Managing the Business Rules(Revision Management)

AppOverlay & Decision Manager Portal configuration:

· Decision Manager portal mainly used for PROD Simulation & PROD. Use an applicationOverlay for development

· Business sandbox & AppOverlay env & Direct deploy for Decision Data update

· Need to configure ADM monitoring, IH, VBD

Building An app overlay application:

· Create New App Overlay wizard and create an app

· Define the accessgroup & list of available rules to expose to AppOverlay to make the changes. Primarily on Decision data.

· Default application Overlay will be created after Landing opage. The name of the overlay starts with ‘RTC-‘.

· Start the Application Overlay wizard via the Decisioning > Infrastructure > Revision Management->Application Overlays landing page.

· Define the AppOverlay applicaiton, Revision ruleset, accessgroup & the Rules to be included as part of AppOverlay

· Selet the rules to make available for the revision Management, select the rules and click "Include for Revision Management"

· Review the AppOverlay and credit the AppOverlay application

· Setup new accessgroups & their roles and the required operator IDs to use.

Managing the Business Rules(Revision Management):

Has 3 envs in PROD (build-Sandbox, test-sandbox and prod).Revision Management enabled business users to make the change with the limited rules.

Post every release, AppOverlay reset will be done in the dev environment (PROD-AUTH). ie, new version of the app overlay will be created. Post creation, completed package will be deployed in business sandbox (Simulation) followed by PROD like regular BAU release.

· AppOverlay release & package deployment as part of BAU release has to be explored.

· The process to create a version & export is based on the dynamic case management process

· As part of Revision management, CRs will be created by Revision Manager and the change will be implemented by Strategy Designer. Revision manager will approve/Reject the CR

New AppOverlay version will be installed like below:

· The System Architect can use the revision activation landing page which can be found at Decisioning -> Infrastructure -> Revision Management -> Revisions.

· These revisions are primarily used to implement the config parameter to alter the decision application behavior

· To sendback the CR to the RevisionManager, use SendBack CR option incase any additional RuleSet access required.

· Once you submit the Revision, jar package file will be generated. We need to download them.

· To implement the changes in pre-prod & Prod environment, Decisioning -> Infrastructure -> Revision Management -> Revisions->Import revision

· Select the Operator from the available list to test the changes for the selected operators before promoting the change.Decisioning -> Infrastructure -> Revision Management -> Revisions->"Activate" the change. Change will be activated to all the users. We can roll-back if needed

· After activating the package, we need to logout and login again

Working with the Revision Management is 2 set process. 1. Create Revision. 2. Create CR. We can have more than 1 CR in a given Revision. Once Revision Submitted, Jar will be generated. If the change is not working, we can revert the change by doing "Roll-back", otherwise activate the Revision.

More details about app overlay setup is available at https://community.pega.com/knowledgebase/articles/decision-management-overview/applying-changes-business-rules

Happy Learning!

PEGA Decisioning (DSM) - Strategy Design Patterns

2020-10-11T00:13:00.000+05:30

Avoid Redundant Product Offers in PEGA Decisioning Strategy

To avoid the same product recommendation which customers own already, from PEGA we need to define the data relationship using DataFlow. For example, to cater to a use case where a customer owns multiple products and details of all products are available in a Product master table. So, there is a one-to-one relationship between the ProductHoldings and Product entities.

Now to implement the business case discussed (Filter the products already owned by the customer), you must filter out the products already owned by the customer. For this, you use a strategy pattern that is composed of three components: Data Import, Data Join and Filter, we can filter out the products which customer is holding already. DataImport+DataJoin+Filter is the Strategy design pattern used to achieve.

Making NBA more relevant using Interaction History - Learn from IH (Interaction History)

Update the Strategy to include a component that retrieves Interaction History data for previous phone offers. We then filter out phone offers for customers that have accepted a phone offer in the past. We can of course make the filtering process much more sophisticated by considering phone upgrades, etc. But for the sake of our demonstration, we will keep the strategy simple; anyone who has been made a phone offer within the last 120 days will not be made another phone offer of any kind. IH+GroupBy+Filter is the Strategy pattern used to prevent Redundant offer recommendation in PEGA Strategy logic.

Interaction History Data model in PEGA7 & Extending the IH Data Model

2020-10-11T00:07:00.000+05:30

Interaction History users STAR schema (Inherited from Cordiant framework) uses 1 FACT table and 8 Dimensions table. DIM table always has non-duplicate reference records which can be referred in FACT table using PK-FK relationship. IH table stores all Interactions in IH Tables through pegaDATA schema.

For more details, refer the PDN article- https://community.pega.com/knowledgebase/articles/decision-management-overview/interaction-history-data-model-pega-72-73

We can also extend the PEGA’s IH table. Below PDN reference article has all the needed information - https://community.pega.com/knowledgebase/articles/decision-management-overview/extending-interaction-history

The process of extending the Interaction History layer in your application consists of the following steps:

1. Adding columns in a database table

a. Write a alter sql statement to alter the IH Table

2. Adding extensions in application rulesets

a. Perform the following actions to extend Interaction History with the HandleTime property for the call center application:

i. Add a new property HandleTime of type Integer to the Data-Decision-IH-Fact data model in the application ruleset of the call center application.

ii. Add the HandleProperty to the SR class of the call center application.

iii. Override the pyInteractionHistoryConfiguration data transform in Data-Decision-IH-Configuration for the call center ruleset:

1. Add a Set action and set Primary.pyFactProperties(<APPEND>) to "HandleTime".

2. Add a Set action and set Primary.pyMeasurements(<APPEND>) to "HandleTime". This step is necessary so that you can use the property as a KPI.

3. Enable the Call superclass data transform setting.

Happy Learning!

PEGA Decisioning - Predicting Customer Behavior Using Real-time Data

2020-09-27T13:54:00.001+05:30

· Applying adaptive analytics to your strategies will enable them to detect changes in customer behavior as they occur and act on them immediately

· Adaptive Decision Manager is a closed-loop system that automates the model creation, deployment, and monitoring process. It can manage a large number of models without human intervention.

· ADM can capture and analyzing response data in real-time. cases where data is available for offline modeling, predictive models can be used as an alternative, or in conjunction.

· ADM models to be created under Customer class, Decisioining, Adaptive Model

· Any Single value Property from Customer class can be a predictor. It can be added under Predictors tab. It can be either symbolic/Numeric. PEGA ADM will automatically remove the unused predictors

· Define Positive & Negative Outcomes under Outcome Tab

· On the Settings tab of the Adaptive Model rule instance, you can define values that will fine tune the behavior of a model as a whole. For example, the ‘Performance threshold’ value is a limit that indicates that any predictor performing below this threshold will not be used to predict customer behavior.

· When you configure an adaptive model record no models are created. The models are created on-the-fly, once there is demand for a given model. When it evaluates the Adaptive Model component, it requests the propensity for each single proposition or channel combination that is dictated by the component inputs. If the models do not exist, they are created at this time

· It is strongly recommended that you set both the channel (.pyChannel) and the direction (.pyDirection) properties in your strategies before you use adaptive models. The channel and direction settings enable you to make decisions based on customer behavior in a specific channel.

· Adaptive Model Outputs - Propensity, Performance, and Evidence

Propensity – This is the predicted likelihood of positive behavior. Such as, the likelihood of a customer accepting an offer. The propensity for every proposition starts at 0.5 or 50% (the same as a flip of a coin) because in the beginning the model has no response behavior on which to base its predictions.

Performance: This is how well the model is able to differentiate between positive and negative behavior. Again, the initial value for each model is 0.5, with 1.0 being perfect performance. Therefore, the performance value should be somewhere between 0.5 and 1.0. Performance is generally used to differentiate between two models relating to the same proposition.

Evidence: – The number of responses used in the calculation of the Propensity.

In strategies, model propensity is automatically mapped to the strategy property called .pyPropensity.

There is no automatic mapping for the Performance or Evidence outputs. But they can be manually mapped to any of the strategy properties under the Output mapping tab (ModelEvidence, ModelPerformance).

Smoothened Propensity: To reduce the ADM Propensity error in early days.

(@divide(.StartingEvidence, (.StartingEvidence + .ModelEvidence+1.0),3) * .StartingPropensity) +

(@divide(.ModelEvidence, (.StartingEvidence + .ModelEvidence+1.0), 3)*.pyPropensity)

Where: Starting Evidence and Starting Propensity are proposition properties representing the assumed values for evidence and propensity.

Pega Decision Management uses “Coefficient of Concordance” (CoC) to measure the performance of predictors and models.

Trend Deduction:

· How to measure the performance of the new Proposition using Adaptive, Trend Deduction.

· Define the required Predictors, Outcome (keydown will prompt IH Data options) and memory settings (Run analysis after 500 records)

How to define More than one ADM for the same propositions?

· Define the 2 diff ADMS using different Memory settings

· Add 2 ADMs and add GroupBy Proposition (pxIdentifier) with the highest performance. Now, we should able to select the highest performance Proposition.

All ADM models Management options can be found under ADM Management.

o Clear Model - Clears the model responses

o Delete Model - Removes the physical model

o View Model Properties - see the settings of an Individual Model parameters

o Upload Responses will allow you to import the Historical data. upload the CSV file and map the outcome.

Monitoring the Adaptive Models:

· DS->Decisioining->Monitoring->Adaptive Models Reporting

· You can analyze the Behavior report under Reports to analyze the Active/Inactive predictors. Also the Classifier allows you to analyze the propensity.

· Performance Model allows you to analyze the performance of the ADM

· The Predictors overview will enable you to analyst the various predictors defined

The implementation of the Next-Best-Action mechanism is a staged process with each stage refining the proposition selection process.

PEGA Decisioning - Avoiding Loan Default with Predictive Analytics

2020-09-27T13:52:00.002+05:30

For predictive analytics algorithms to work we must have access to historical data which exhibits known customer behavior. We must also know what problem we are trying to solve in our case probability to default.

These fields are called predictors and are combined into a predictive model which you can use in your business processes.

Predective Model involves 5 Steps:

Data preparation, Data analysis, Model development, Model analysis, Model export

Predictive analytics director supports two types of models:

· Scoring Models - for the prediction of binary behavior

· Spectrum Models - for the prediction of continuous behavior

Scoring Models:

The value calculated by the model, known as the score, places a case on a numerical scale. High scores are associated with better business (good behavior) and low scores are associated with worse (bad behavior). Typically, the range of scores is broken into intervals of increasing likelihood of one of the two types of behavior. Scoring models require behavior to be classified into two distinct forms like positive and negative. Classic examples of such behavior are:

· Responding to a mailing or not

· Repaying loans or going into arrears

Spectrum Models:

Spectrum models extend the ideas of scoring models to the prediction of continuous behavior

· Likely purchase value of responders to a direct mail campaign

· The likely eventual write-off of cases recently falling into arrears

Model Template:

In the Predictive Analytics Director portal we have defined a number of model templates which you can use. These include Risk, Retention, Recruitment, and Recommendation.

Select the appropriate Model Template and start working on the Project

1) Model Creation:

· Select source as CSV file or DB

· Set the Sampling size using % & tot. cases. Define the properties to be used and the type of the property

· You identify the field which you are trying to predict. In this example, the field is behavior. The field exhibits binary characteristics (N/Y) so the scoring model is the most appropriate.

· Now define Good & Bad behavior under Outcome definition.

2) Data Analysis:

· Predictive Analytics Director facilitates automatic discovery of correlation patterns of individual predictors and their ability to predict the outcome. Any unique identifiers will not be a valid predictors. customer ID appears to be a reasonably well performing predictor. However, since we know that customer ID is a random number or a member of a sequence, it cannot have any impact on the good or bad behavior. Thus we remove IDs from the candidate list for predictors. Any property which is common to use to differentiate the good and bad behaviors can go as a predictor

· So data analysis involved in defining the properties & Binning (Split the data into Buckets) and then grouping by predictors.

3) Model Development:

· Predictive Analytics Director provides a rich model factory supporting industry standard models such a regression and decision tree models.

· The system automatically creates two models: the Regression and the Decision Tree-CHAID model. At this stage, you can create additional models if required.

· We can group the predictors into Group,. Which means either Predictor A/B/C outcome will be considered. Eg. HouseOwner/Rented etc.

· Also look at the scorecard representation model to check the scores of the predictor and define the weight of the predictor from 0-1000

4) Model Analysis:

· Model Analysis is to enable you to create a shortlist of models and then select the best model for your use case. At this stage, you also group the scores into statistically significant set of score bands; firstly, let’s examine the relative performance of individual models.

· A very important aspect of each model is its performance, i.e. how good is a model or a given predictor in predicting the required behavior. We use a term “Coefficient of Concordance” or (CoC) for the measure of the performance of predictors and models. You could describe CoC as a measure of how good the model is in discriminating between good cases from bad cases. The value of CoC ranges between 50%: a random distribution, and 100%: the perfect discrimination.

· Analyze the Models created and select the models where how good the model is in discriminating between good cases from bad cases.

· There are following steps in Model analysis: Score Comparison, Score Distribution and Class Comparison.

5) Model Export:

· In the final stage, you can produce the reports about the model and export the model into a model file or an instance of the Predictive Model rule. Check the customer properties and the predictors created in the model under input mapping.

· The report contains:

1. A project summary

2. A visualization of the whole Decision Tree

3. The sensitivity of the model for each of the input fields

4. Model segmentation

5. Detailed insight in the analysis, grouping, and validation of each of the attributes

6. Date when the model was developed and by

PEGA Decisioning - Avoiding Redundant Product Offers to Customers

2020-08-22T14:18:00.002+05:30

How to make the Offer recommended to the Customer is Personalized? One basic eligibility check is by avoiding Redundant Product Offers to Customers

If customer already have the Products, don't offer them.
We can extend the Customer DataModel by defining the 1-1 OR 1-n relationship of the customer owned Products/services. For example, a list of purchases made, a list of accounts owned, a list of family members, and a list of services owned.
You can define the Relationship between Customer class & Product class
You can build the Custom DataFlow to populate the customer Profile information composing other Data properties
Nested Data Type also possible. We need to discuss and agree with the Data Model & compose the same with the respective class object
When u use the Data Join, the target mapping always be the SR class properties and the source can be customer class properties OR another SR class properties
Data-Join component allows you to join 2 sets of data and map to the SR class properties
Filter component Filter can be plain Filter condition (Takes Customer class properties & SR class properties) OR it can be a Proposition Filter.
@and(booleanA, booleanB) validates to TRUE if both the conditions met
When u connects with the newly created DB table, create the Table and respective classes through DB Class mapping wizard.
Go to Data Model -> Classes & Properties -> Database Class Mappings landing page. Click New External Database Table Class Mapping.
Use DataImport component to Import the Data from External DB Table contents.

Happy Learning!

PEGA Decisioning - Balancing Business Objectives and customer needs

2020-08-21T13:53:00.002+05:30

To Balancing Business Objectives and customer needs, its good to remember the following points.

Always-On customer brain stands behind the NextBestAction
Business Logic is an iterative development. We will develop with the current requirement and based on the customer behavior, we will change the Strategy
The Key Elements in Implementing the Business Logic is:
Business Issue * Group. All propositions will be added under any specific Group only
Propositions - Proposition Catalogue will be maintained
Prioritization - BL-Strategy
Use the NBAM components to implement the logic Strategy. ADM is used to predict the customer Propensity and learning the data real-time.
Predictive models will be used to learn from Existing models
All Decisioning Strategy business rules are classified under Hard & Soft Rules. Eligibility rules are Hard rules and all Decision Data (Control param), Arbitration components are Soft rules
Break the whole logic into Small sub strategies logically and process the Propositions in each stage to apply the proposition selection process
Eligibility Rules are always determined as Hard Rules
Prioritization component will be used to determine the Top offer at any given time.
BusinessIssue and Group is something we want to think first before implementing NBAM project
NBAM project is not a finished product. We want to learn and make the continuous changes to make the better decision

Apply BML methodology to keep optimizing the Strategies to drive the business outcome
B-Build - Make the Strategy/Logic changes
M-Measure - Measure the performance of the Strategy
L-Learn - Learn the feedback from Customer

Repeat the BML method again.

Happy Learning!