Extreme couponing is not only one of these weird shows on TLC, it’s also more and more a way of living for many households. Since January is generally one of the months where households spend less and are looking to save money in opposition to the bloody months of November and December, I thought it was a timely moment to write a post related to this topic. This post takes a mom blogger approach blended with some of my old-style economist thinking to decorticate the “Real Basket Value” equation and suggests that some extreme couponing behaviors may increase the “Real Basket Value” instead of decreasing it. This post is written purely from a customer perspective rather than from a retailer perspective. So let’s get it started by presenting the “Real Basket Value” equation related to a specific transaction at a retailer:

Basket Price + Direct Costs + Externalities = Real Basket Value

Real Basket Value - It's Not Only What's in the Basket When Shopping at a Retailer

Basket Price

Let’s first start with the easiest part of the equation, the Basket Price. The Basket Price is defined as the nominal price of all items included in the basket you will buy at a retailer. This is the price you happily or unhappily see on your bill.

Direct Costs

Direct costs may be restricted to distance costs, which can be defined as the additional costs related to the act of moving from point A (Generally your home or your workplace) to point B (the retailer where you will buy your items). These distance costs may include the amount for gas you will spend to make the distance and the depreciation cost of your car related to this particular ride. In some cases you may fix these costs at 0, while in other cases, they may be not as negligible.

Externalities

Externalities are forgotten by many households since they may look frivolous, but the reality is that they may, and sometimes should, have an impact on the “Real Basket Value” equation and in the final decision of: (1) where to shop/buy, (2) what to buy and (3) in how much quantities? An externality is defined as a cost or benefit that is not transmitted through direct prices.

Most importantly, externalities include time costs. As Benjamin Franklin stated, “time is money”, since time is a scarcity that can be associated to a particular opportunity cost. Some components of “Time costs” are a function of distance costs while some others are not. For instance, the time spent in traffic to reach a retailer is a function of the distance cost while the time spent searching for THE discount is not.

Furthermore, many other costs and benefits could/should also be taken into account. These include: (1) the benefits associated to the loyalty programs points you are gaining in buying what you are buying, (2) the stockpiling costs, (3) the costs or benefits associated to how much life expectancy (including medical costs) you are gaining or losing buying high or low quality food, and (4) the costs or benefits associated to your joy of buying (and most importantly thereafter consuming) a certain type of product that is offered at a particular retailer.

More About the “Real Basket Value” Equation

To fully take advantage of this humble equation, you can do a quick benchmark between two or more retailers or run the equation again by manipulating components of this equation. Thereafter, using heuristics (reflex or shortcuts) may be the optimal way to reduce the “real basket value” by cutting useless overthinking.

Conclusion

Happy new year to everyone, enjoy the year 2012 shopping efficiently and don’t spend too much time finding THE “right” coupon.

Cheers,

Jean-Francois

Share/Save

The sentence “I’ll be traveling with Air Miles in 2012″ may have different meanings. However, It will become clearer what it means for me in the next few paragraphs.

I know I’ve been relatively absent from the social web for the last three months, except maybe on the LinkedIn website, where I’ve been more active than usual. That being said, many changes have occurred during that 3-month period from a professional perspective and it will impact the content of my blog in 2012.

As a matter of fact, I’ve accepted a position as a Partner (Manager) in the Consumer Intelligence (CI) Department at LoyaltyOne (a division of Alliance Data). As part of the LoyaltyOne company, my role involves working for the Air Miles Reward Program (AMRP) at the Montreal Office. My first week of work was last week (starting on December 5th) and I enjoyed it. The main reason for accepting this opportunity was based on my desire to participate more actively to the dissemination and improvement of the “competing on analytics” philosophy in the practitioner’s world. Overall, my decision to join LoyaltyOne was based on 6 factors, which I ordered in a hierarchical way.

1. Office in Montreal
2. Availability of a managerial position
3. High analytic potential
4. Company’s potential growth
5. Work life balance
6. Salary

Among all of these factors, the following factors will influence the most the content of this blog: (1) availability of a managerial position, (2) high analytic potential and (3) company’s potential growth. However, for confidentiality reasons, I won’t be able to report any practices or data methods developed through my work at LoyaltyOne as long as it will be considered as confidential information. In any ways, I’ll be happy to share what can be shared.

The Air Miles Reward Program (AMRP) Card

More about Alliance Data, LoyaltyOne and the Air Miles Reward Program

Alliance Data: www.alliancedata.com
Headquarters: Plano, TX
Founded: 1996 (from a merger of JC Penney’s transaction services business (BSI Business Services, Inc.) and The Limited’s credit card bank operation).

LoyaltyOne: loyalty.com
Headquarters: Toronto, Ontario
Founded: 1992

Air Miles Reward Program (AMRP): airmiles.ca
Founded: 1992
Sponsors: More than 120 sponsors

For more about the history of the company, visit the Wikipedia page for Alliance Data.

How does it change this blog?

• More blog posts than in the last 3 months;
• More managerial insights based on analytics;
• More posts on retailing and loyalty marketing;
• More fun.

Conclusion

The Holidays are coming soon, which means that for many of us, it’s the last rush before the end of the year. Good luck to everyone and when shopping don’t forget to use effectively your Air Miles card when applicable,

Enjoy time with your family and friends, and Happy Holidays to everyone!

Jean-Francois Belisle

Share/Save

Hey kids and University students, it’s time to go back to school and enjoy learning with top notch educators. And if you’re looking for a way to “waste” your time on social media (it may transfer into an “investment” in the long-run but its usually a short-term waste), there are still old social networks available to you such as Facebook, Twitter and Tumblr, or maybe you could try Google+, if it’s not already done. This introduction sounds like it was composed for a Barney’s commercial, but anyway!

Google+ Google Plus G+

I am back from the AMA Summer Conference at San Francisco, where I presented and attended a great conference. The best session I attended was a special session entitled “The Sustainability Imperative and Marketing” organized by distinguished Professor Rajan Varadarajan and featuring “influence guru” Robert Cialdini. Even though it wasn’t really framed as an academic presentations, I mainly liked it since it applies social norms theories to real-world cases and was measured by clear outcomes right at the end of the conversion funnel, the authors were not measuring attitudes or intentions, they were measuring real behaviors, like it should be. Furthermore, during my stay in San Francisco, I noticed that my number of followers on Google+ had risen a little, you social folks! Since I am back, I also noticed, that some articles reported a slow rise or even a decline in the first few weeks of the social network’s existence, so what? Summer is a dead season for social networks, many people enjoy their vacations, and other enjoys good times away from all types of screens. Taking a position on these numbers would look like GIGO to me, politely referred to in computer science as “Garbage In, Garbage Out”.

Google Wave and Google+

In a post entitled “Fighting for the Web Supremacy: How Will Google Wave Suffer from Switching Costs and Lock-In Against Facebook”, taking the Google Wave case as an example, I suggested that the lock-in effect may dictate if users are going to embrace a new product or not. Even if the new product is better than the old ones, the “heavy” switching costs may have a dominant impact on the decision to switch when compared to the benefits. In terms of a social network, the investment is even bigger, since most people can’t handle more than 2 or 3 social networks, even if there exists some aggregating tools. Most importantly, most people are participating in a social network if their friends are there. There is no point of sharing information on an empty social network unless you want to be the king of nothing. Finally, the lock-in effect may have actually won over Google Wave, but I guess that no clear benefits were there for the typical user due to: (1) a lack of user friendly functionalities, (2) a lack of integration to existing Google services, and (3) there was nothing really trendy offered to the user.

Back to School and Social Media

Like previously mentioned, summer is a dead season for social networks and I must admit that launching Google+ on June 28th 2011 was not a bad idea. Generally, in the first few weeks of a social network’s existence, only social media enthusiasts register to new social networks, the bugs get fixed and thereafter the crowd decides to come or not to come. When it comes to social networks initial growth, it’s all about youth and young adults and most importantly about University Students. Some geeks will always pick up new products, even if they sometimes literally “suck”, because they want to be perceived as “precursors”, or in terms of the Bass Model terminology as “innovators”. However, only a small portion of these “precursors” may thereafter act as mavens for the non-technological/ubersocial crowds.

So why back-to-school and University students? First, students are a large portion of social networks user. Second, when workers are switching jobs and connecting with new colleagues, not all workers are switching at the same time, some might never switch and might always work with the same colleagues. On the other side, when University students go back to school for the academic year, they all go back at the same time. Overall, if there is one time students make more “new” friends/connections, it’s in the beginning of the academic year, it’s all about the “initiations”, new classmates, sometimes it’s time to chit-chat with serious folks that are more friendly than during the rest of the year, to enlarge your friends’ network, to have fun and to exchange links. It may also be time for love.

More on Google+

If you want more articles about Google+, feel free to follow these links:
- Tons of useful and useless articles related to Google+ on Mashable
- Great SWOT analysis of Google+ by Jeremiah Owyang
- Google+ in 50 points by Chris Brogan
- To add me to one of your Google+ circles, you can follow this tiny URL: goog.la/jfbelisle

Conclusion

In conclusion, in the next three months (September, October and November), we’ll see if Google+ is a failure or a success. How will the youths and young adults react? Odds are that it might be better than Google Wave, will that be enough against forceful Facebook? Let’s wait and see before being overoptimistic. Any additional comments?

Have a great semester everyone!

Jean-Francois

Share/Save

Strategic Marketing thoughts and analytics are the future of business. This first sentence reflects my own opinion and is mainly written for search engines, the rest is not for machines but for you readers, .

I have been digitally absent during the last two months to focus on my PhD dissertation, challenging strategic marketing research-related projects and also to enjoy summer. After participating at both the Web Analytics Quebec Canada first UnConference and the ASAC conference, both held in Montreal, I then went on vacations on a 13-day road trip on Route 138 right away to the far east of the Côte-Nord region. It’s always great to discover the beauties from around the world, but part of this beauty may be found locally too. I’m back to work since last Monday (July 25th), 3,226 kilometers later along with a heavy 5-week growing beard similar to Brian “fear the beard” Wilson (we nearly have the same age, same height and we’ll both be in San Francisco next week, so I felt the comparison was of circumstances) that I will soon shave even though many Asian friends have already envied me.

My main guidance for this trip was hardcopies of pdf touristic guides and most iPhone applications were irrelevant during that trip, the only three I used were the WeatherEye, the Pedometer and the Maps applications.

The objective of this trip was to explore nature along with my girlfriend and relax. However, even though this trip has nothing really business-related, I decided that a “short” post on the business-related issues and marketing concepts I encountered could include interesting strategic marketing thoughts to share. Ready for the story? 13 days = 13 strategic marketing thoughts.

Day 1 – Montreal -> Quebec City OR The Dropkick Murphys Brand

I ended up the day attending at the “Festival d’été de Québec” two shows targeted to two diametrically opposite crowds: Dropkick Murphys and 12 Hommes Rapaillés. Here I will mainly focus on the first one from a brand perspective.

The first one was the Dropkick Murphys, an Irish-punk-rock band from Boston, Massachusetts and proud to come from there, a band I have been following since their beginning in the late 90’s, mostly known to the mainstream audience for the song “Shipping up to Boston” which appeared in the award-winning movie “The Departed”. As a “brand”, the band heavily represents the city of Boston wherever they play by generally wearing sports jerseys from Boston sports team, especially the Boston Bruins and Boston Red Sox. They are also connected to some of the players. The Quebec crowd even had a special guest when Patrice Bergeron from the Boston Bruins made a special appearance on stage. The guitarist Ken Casey wore a Boston Bruins jersey with the number 4 in honor of Bobby Orr. In terms of brand congruency, the Dropkick Murphys brand is a great marketing example. It was thereafter time to grab a delightful beer at l’Inox before the next show.

Day 2 – Quebec City -> La Malbaie OR Charlevoix Famous Road Signals

After an employee noted my vehicle registration plate at Ste-Anne-de-Beaupré for touristic calculations purposes, we then headed up to the Charlevoix region. Forget about the agro-tourism, forget about artistic gifts, my main attraction when entering the Charlevoix region was to learn how to manage the use of my car brakes while dealing with the famous road signals such as the 18% hill slope at St-Joseph-de-la-Rive, a small town sadly known for Canadian most fatal accident when a bus crashes in the hill in 1997, killing 44 passengers; the slope is more secured since, but still heavy for brakes. On the other side, these high percentage hill slopes (between 8% and 18% at many places) are extremely great marketing signals to get more tourists which can be labeled as “adventurers”.

An Urgency Breaking Area in Charlevoix, Great for Security and Great for Adventurers from a strategic marketing perspective

Day 3 – La Malbaie < -> Parc des Hautes-Gorges OR The Scarecrows Village

On the road to Parc des Hautes-Gorges, I was happily surprised by all the scarecrows I seen in St-Aimé-des-Lacs village, carefully handmade to make the village more enjoyable during the “Rodéo de Charlevoix” event that was held the month before. I find it a great way to build the branding of the village, unless you are scared by the Scarecrow in the Wizard of Oz.

Day 4 – La Malbaie -> Tadoussac OR The Whale Watching Industry

Tadoussac is a small touristic town with 850 people, but what it is mostly known for is its presence near the Saguenay Fjord, which makes it a perfect place for Whale Tourism. Before watching some whales, belugas and porpoises, I had some time to study the structure of the Whale Watching Tourism market which is mainly a duopoly where you have two generalist well-implemented players, AML and Dufour, while some smaller players such as Otis are also present. You can even buy tickets for Whale Watching in a 60-kilometer radius of Tadoussac. All in all, it was a nice small town with high prices that remembers me Norway and a high percentage of tourists from France. I had the worst bargain in terms of hotel prices of the entire road trip but that’s part of the game I guess!

Day 5 – Tadoussac -> Baie Comeau OR The Sushi Restaurant in Baie Comeau

When I arrived to Baie-Comeau, I was hungry and I don’t remember why but ended up watching the ad of a Sushi restaurant offering Japanese, Chinese and Vietnamese food, all at the same time. From a Montrealer’s perspective, it first looks to me like a lack focus signaling a lack of quality. However, since the competition for Asian food is certainly lower in Baie Comeau than in Montreal, I guess that including more food types may be a great way to wider the audience in a smaller market. In a big city, this strategy would signal “lower quality” and would result in a wide audience reach but a low conversion rate. Any strategic marketing thoughts on this one? Anyone wants to conduct a field experiment with a 2 (focus: High vs. Low) X 2(City size: High vs. Low) experimental design with sales as a dependent variable? Finally, we ate some macaroni with cheese, anyway.

Day 6 – Baie Comeau -> Sept-Iles OR Manic-2 and Strategic Marketing

Day 6 started and culminated with the visit of the Manic-2 hydroelectric dam 22 kilometers north to Baie Comeau on route 389. The whole presentation was correct, but what really surprised me, and my girlfriend even more, was the way the presentation was framed. Since the hydroelectric dam is the property of Hydro-Quebec, the staff was trained to present a “pro-Hydro-Quebec” point of view rather than a scientific speech. I even had to fill a “Hydro-Quebec is great” survey at the end. Call it lack of transparency, call it great advertising, call what you want, at the end of the day, I would have done the same if I were Hydro-Quebec anyway!

Jean-Lesage Generating Station, mostly known as "Manic-2" near Baie-Comeau

Day 7 – Sept-Iles -> Longue-Pointe-de-Mingan OR My Favorite Brand was AfterBite

This day was a global maximum (a culminating point) in terms of mosquito abundance, even equipped with my newly bought hunter orange cap; I can tell you that we lost the fight against mosquitoes. Anyway, my favorite brand for that day was AfterBite, and if I would have been a commerce manager, I would have put a rack full of these, right after the twilight zone.

Day 8 – Longue-Pointe-de-Mingan < -> Natashquan OR Bigger Than His Town

On Day 8, I finally reached the end of the road populated by lunar landscapes and plenty of bogs, and visited Natashquan, also known as Gilles Vigneault‘s village as popularized in his poems/songs. For the younger generation, with at least three honorific doctorates, Gilles Vigneault is to Natashquan what storyteller and singer Fred Pellerin is trying to be for St-Élie-de-Caxton. If there something I can say about Natashquan is that the city officers better take even more advantage of Gilles Vigneault’s appurtenance to the village before and after he’ll die, since there are not really a lot of industries that can be developed there due to the geographical location.

Day 9 – Longue-Pointe-de-Mingan -> Moisie OR “Chicouté” All The Way

Heading back on Route 138, this was the day the word “Chicouté” finally stuck in my head. Cloudberry, known in French as “Chicouté” or “Plaquebière” is a little fruit that has the texture of a blueberry and looks more like a raspberry. In anyways, I heard this word so much, that Côte-Nord touristic agents should put some “Chicouté” on the front page of the next Côte-Nord touristic guide since this fruit is so emblematic.

Cloudberry, known in french as or "Chicouté" or "Plaquebiere"

Day 10 – Moisie -> Baie-Trinite OR Drinking Coffee with a Straw at Tim Hortons

This day was mostly about shopping, visiting historical venues and trying my newly bought waterproof pair of boots. However, what really picked up my attention, and even more the one of my girlfriend, was the straw drinking habits of inhabitants ordering at the Tim Hortons in Sept-Iles. Most people were drinking their coffee with a straw which was, and is still, unusual for me. Using some deduction, I could suggest that this phenomenon is due to the fact that most people going to Tim Hortons are blue collars, most blue collars near Sept-Iles drive a lot, especially driving a truck, ranging from a “small” Ford F-150 to a mammoth construction truck, and since roads in Quebec are well-known to be “extremely well-paved and resistant to any climate”, then it would reduce stains to use a straw to drink coffee. I also noticed after surfing the web that drinking coffee with a straw is better for your teeth even though it doesn’t look really glamorous.

Day 11 – Baie-Trinite -> Portneuf-sur-Mer OR I Have a Glaciologist Apprentice License, so What?

Similarly to Day 10, this day was also dedicated to history due to the bad weather and also to my appetite to always learn more. Stories about mining/company city and a multimedia show about glaciology were part of the day. I even earned my “glaciologist apprentice license” while giving the wrong answer to most questions, c’mon, fail me if I suck folks, no pain no gain, even if it was designed for kids. No one is winning when everyone’s winning.

Day 12 – Portneuf-sur-Mer -> Saint-Simeon OR Where Gas is Cheaper

The Sacre-Coeur/Forestville axis on Route 138 is certainly one of the areas with the lowest gas prices in Quebec. After filling my tank full at 1.44 per liter at Aguanish 4 days earlier, I filled it again at 1.27 per liter at Forestville. You can even find more information about gas prices on the web. Low municipal taxes and the proximity to an aboriginal reserve may have explained these prices.

Day 13 – Saint-Simeon -> Montreal OR The Last Tourist Trap

After seeing the car in front of me taking a police ticket after the bridge to Ile-d’Orleans, as a microbrewery fan, I stopped at Ile-d’Orleans near Quebec City for a beer at Ile-d’Orléans microbrewery. Ile-d’Orléans is certainly a beautiful place but what I was surprised is that prices were quite high for the same goods exported from this area that I would buy at a place near my home, let’s say at the Jean-Talon Market or at the 350-different-beer convenience store near my home, maybe storage fees are sometimes higher than transportation fees or it’s all about the markup?

Conclusion

These were great vacations! I hope you enjoyed the little strategic marketing-related story! The next step for me is the Summer AMA Marketing Conference in San Francisco where I will present along with my friend Robert Mackalski, and will attend presentations such as the one by Robert Cialdini. I should be back in two weeks with some more tasty content. Enjoy!

Jean-Francois Belisle

Share/Save

Product-harm crisis and its associated brand spillover effects is a “relevant and spicy topic” in marketing that I am currently investigating in more depth along with colleague Bob Mackalski (more to come concerning this issue on this blog). Similarly, in the last few days, I must admit that the Dominique Strauss-Kahn (DSK) sexual scandal is great food for thoughts (for more details about the May 15th 2011 sexual scandal that happened in New York) concerning these issues but at the employee or connection-level, rather than at the product-level. However, by considering Dominique Strauss-Kahn as a brand, the analogy for analysis is nearly the same. Before writing anything on the topic, one should first decorticate Dominique Strauss-Kahn identity or if you prefer the ecosystem evolving around him. Thus, my objective here is not to give implementable solutions, but simply to expose you which entities can be affected in a public figure failing/scandal. All the information used here is easily available on the web or in newspapers and is reported in an objective fashion. Thus, let’s classify Dominique Strauss-Kahn identity in 6 categories:

1. Origins and ethnicity
2. Institutions
3. Professions
4. Ideology
5. Business Connections
6. Family and friends

Dominique Stauss-Kahn (DSK) - Before the May 15th 2011 Sexual Scandal in New York City

Category 1 – Origins and Ethnicity
1. France
2. French nationality
3. Of Jewish ethnicity

Category 2 – Institutions
1. Managing Director of the International Monetary Fund (IMF)
2. Member of the Socialist Party of France (PS), he was also France Minister for Economics, Finance and Industry from 1997 to 1999. He was expecting to run for France presidency.
3. Full Professor of Macroeconomics and Microeconomics at Sciences-Po
4. Attended High school at the Lycée Carnot
5. Graduated from HEC Paris
6. Graduated from Sciences-Po
7. Graduated from Université Paris X (Nanterre)

Category 3 – Professions
1. Politician
2. Economist

Category 4 – Ideology
1. Considered as a communist in his early life
2. Center-left point of view

Category 5 – Business connections
1. I won’t put names here, simply search them on the web if you want.

Category 6 – Friends and family
1. Parents
2. Married to Anne Sinclair
3. Two other wives from previous weddings
4. Four daughters
5. Other family members
6. All friends

A Quick Analysis

At the end of the day, a quick analysis brings the conclusion that the biggest losers here are:

1. All friends and family
2. Socialist Party of France (PS)
3. All French politicians
4. The French, the people from France
5. IMF
6. Science Po

Next Steps

For sure, for the ecosystem associated closely to Dominique Strauss-Kahn, what needs to be done is to work days and nights to recover, recover and recover as fast as possible. From a purely analytic perspective, the next step would be to measure the short-term and long-term impact of this scandal, qualitatively and quantitatively, and to act accordingly to change perceptions.

Conclusion

At the end of the day, the biggest loser in this scandal is DSK himself, but the harm may be irreversible for some people evolving around him (especially family and friends). Don’t forget that what can strengthen you, can also destroy you!

Enjoy the day (even if it’s raining here), not the scandal,

Jean-Francois Belisle

Share/Save

During the last year, QR codes have popped up from everywhere around me as well as in most marketing circles in North America. However, for many people, QR codes still remain a mystery. This post is a humble attempt to decorticate what QR codes really are, both from a customer’s and an advertiser’s perspective.

A Quick Overview

QR code is an abbreviation for “Quick Response code” intended to allow its content to be decoded at high speed. It was created by Toyota’s subsidiary Denso Wave in 1994, a company that still owns the patent rights but has chosen not to exercise them. The main objective of Denso Wave was to make “code read easily for the reader” (it looks like a bad Japanese translation, but anyway).

More precisely, QR codes refer to a specific two-dimensional matrix-type barcode, readable by QR barcode readers available on most new smartphones models. It consists of black modules arranged in a squared matrix on a white background. The information encoded can be text, URL or other data. Recently, what has mostly emerged in the online marketing community is the used of QR codes for encoding long URLs for offline advertising.

QR Codes Capacity

Similarly to barcodes, QR codes have extremely high data capacity. There actually exist 40 versions of QR codes (see the Denso Wave website for all versions). Each version has a specific “module configuration”, where the module refers to the black and white dots that make up QR codes. Version 1 is a 21 modules by 21 modules square, while version 40 is a 177 modules by 177 modules square. Each higher version number includes four additional modules per side, which suggests that version 41 would be 181 modules by 181 modules. Version 40, when error correction “L” is used (read more on error correction for QR codes), can encode up to 4,296 numeric symbols or 7,089 alphanumeric symbols.

How to Read QR codes?

There exists multiple mobile applications to read QR codes, one can use the QR code scanner integrated in Google Goggles available for the iPhone, and the Android platforms. For iPhone users like me, the Bakodo application is currently the most used (for the iPhone version I have) since it permits to read both barcodes and QR codes.

Who Uses QR codes?

QR codes usage by consumers is still extremely marginal. If you’re in Asia, especially in Japan or South Korea, where it seems mainstream since some years (2009-2010), it may be different, but in North America, maybe not in San Francisco (I will have the answer no later than this August) it is still reserved to geeks, so it’s still time to be considered as innovators (or geeky consumers) but it may change fast.

QR code for Jean-Francois Belisle website

How to Generate QR Codes?

There exists many ways to generate QR codes for your website URLs or any other kind of data. However, the Kaywa website seems to be the reference to generate fast QR codes for your website URLs.

When Should Advertisers Use QR Codes?

Usage of QR codes has been emerging at a fast pace. You can actually put QR codes on cars and buses if you want or on magnetic cards and dishwasher machines (I don’t see the point but …). However, from an advertising perspective, one needs to take into account at least four factors when deciding to include a QR code or not: (1) the amount of data to be stored, (2) the medium used, (3) the space available for the ad, and (4) how it may alter the ad design.

From a web tracking perspective, QR codes should be used to target any marketing campaign even when the URL is extremely short. However, if you’re tracking a campaign properly using tools to separate sources such as Google link builder, your campaign should always have a long URL anyway. In exceptional cases, if you have a short website URL, you may want not to include QR codes for lack of space and/or not to alter the design. This may be the case for small ads in magazines or TV ads. However, on magazines and especially on billboards, I am a huge advocate of including QR codes.

QR codes should be seen as complements to website URLs on an ad, not as substitutes, since you may reach different types of consumers. Anyway, rarely you will encounter a consumer both scanning a QR code and typing a web URL after.

If there is a place where QR codes are useless for encoding URLs, it’s on the web. Which consumer will want to scan a barcode when on the web to get access to a URL using another device? It may happen, but I don’t see the benefits compared to the disadvantages it may bring by altering the design.

Pepsi QR Code Campaign for Pepsi Max

How to Track QR Codes?

Like mobile technology, QR codes are useful for tracking campaigns even though they for sure underestimate the number of consumers who have seen an ad. For more about how to use QR codes for web tracking using Google Analytics, Publicinsite got an excellent post on the issue entitled “QR codes and Google Analytics to track mobile devices”.

Conclusion

QR codes may not be as sexy as social media, but similarly to tiny URLs, they are around to stay. After the emergence of location-based services, they are another technological innovation that pushes in the direction of connecting the offline world to the online ecosystem in a multichannel marketing fashion.

Enjoy your QR code quest with your mobile device,

Jean-Francois Belisle

Share/Save

This blog is now 2 years old and I’m happily surprised of its evolution during that period. Overall, the blog has reached an average of approximately 2150 visitors per month for the last three months. It has reached a diversified audience visiting from the United States (27%), Canada (22%), and from 127 other countries around the world, from the United Kingdom (UK) to Germany, from India to Australia. 54 posts, 295 comments posted by well-informed readers, and 3773 spams deleted (thanks to the Akismet plug-in) later, this blog has continuously evolved, and will continue to evolve as long as I continue to evolve as a person. Thanks to PhD colleagues, ex-students, ex-colleagues, practitioners’ friends and web enthusiasts who have visited this blog during the last 2 years.

This Blog is 2 Years-Old

I’m satisfied of the outcomes related to the time devoted to learn how to blog properly in search of a WOW effect, how to use the WordPress plug-ins adequately and how to answer amazing comments, while learning and gaining insights from these comments and discussions. This blog has also been a versatile way for me to apply tips and thoughts learned from consulting, research and teaching.

More like a Website less like a Blog

More and more, this blog has become part of an entire website. New sections entitled “Consulting”, “Speaking” and “Useful Links” have been recently added. Look for more sections and especially links to useful resources to come during the next year.

A New Headline: Marketing, Analytics & Entertainment

I’ve recently changed the headline of the whole website from “E-Marketing, Analytics & Entertainment” to “Marketing, Analytics & Entertainment”.

I changed “E-Marketing” to “Marketing”, keeping the online marketing portion but orienting the discussion towards an integrated view of marketing rather than a more restricted one.

I also decided to drop “Technology”, since technology is mostly related to tools and I don’t think I can really compete with gadgets-and-tools-oriented websites such as “Mashable”, “TechCrunch” or “ReadWriteWeb” for audience concerning technology. However, how marketers and statisticians use technology to get insights is more important to me than describing a new technology. Furthermore, this blog is moving more towards analytics, such as web analytics, data mining, business intelligence and statistics. My last three posts are crystal-clear examples of this type of post, but posts such as My Top 10 Superbowl Commercials for 2011 will remain part of this blog. I also recently added a plug-in to add equations in LaTeX, but don’t worry this blog won’t become flooded with equations. Thus, tools and technology will still be discussed, but especially as a support for analytics and entertainment.

I kept the word “Entertainment”, since I thought writing in an entertaining fashion or writing about entertainment in a geeky fashion is a pleasure for me and I hope for the reader/you too. I personally don’t think I am boring person and I don’t want this blog to be boring. The day I’ll stop joking, that day I’ll stop blogging.

In Search of Quality Rather than Quantity – A New Schedule

If there is something I learned during my PhD studies is that quality is even more important than quantity. I get “spammed” by bloggers who posts too much information and of too low-quality. Quantity of bad or average quality is spam for me. I don’t want to overwhelm anyone with too many posts and I personally don’t have time to overwhelm anyone, quality is my objective. A clear example that comes from the academic world is that from an expertise point of view, you’re better off writing fewer papers that are of great quality and that will receive more citations, than to write many crappy papers published in obscure journals that will get no citation except self-citations. In this sense, this blog has recently moved towards a biweekly schedule, which means that there will be a post every two week, except during vacations where no posts will be published.

The Newsletter to Follow More Easily

As a last point, if you want to have biweekly updates of this blog, feel free to register to the blog via either e-mail or via RSS feed reader, these are clear practical ways to receive updates without having to type the website URL every time.

Conclusion

Enjoy the hockey playoffs, enjoy your exams if you still have some to complete, enjoy Summer, and as a conclusion enjoy my blog!

Cheers,

Jean-Francois Belisle

Share/Save

I spent the last few weeks digging deeper into time series-related methods and data mining methods. For this post, I have decided to write a broad introduction related to the latter (data mining), since it may look more practical and also trendier than time-series (but watch out with the emergence of Particle Filtering and other Sequential Monte Carlo methods (SMC)).

Introduction to Data Mining and Criss Angel

So what is data mining? Data mining can be defined as the process but also the “art” of discovering/mining patterns, meaning and insights in large datasets by using statistical and computational methods. In other words, a data miner is like a Criss Angel (You can pick any other magician here!) that will make appear from your messy ocean of data, insights that will be valuable to your company and may give you a competitive advantage compared to your competitors; simply read Tom Davenport’s bestselling book “Competing on Analytics: The New Science of Winning” if you’re not convinced yet about the power of analytics and by extension of data mining. Furthermore, data mining related tasks are also considered as part of a more general process called Knowledge discovery in databases (KDD) which includes the “art” of collecting the right data as well as organizing and cleaning these data, which are also extremely important tasks prior to analyzing the data.

Some Brief History and a Link to Business Intelligence

Data mining mainly takes its roots from the fields of Statistics and Computer Science (some might say Artificial Intelligence) and may also be referred as “Statistical Learning”. From a statistical perspective, most early and recent advances coming from Statistics have come from the Stanford Statistics department school of thoughts (Leo Breiman (was at UC Berkeley), Bradley Efron, Jerome H. Friedman, Trevor Hastie and Robert Tibshirani). By the way, don’t forget that Stanford University is only 7 miles away from Google. Furthermore, the emerging field of Business Intelligence has blossomed as a combination of: (1) data mining tasks, (2) information systems technology and (3) crispy marketing insights.

Professor Leo Breiman - Considered As The Founder of the field of Data Mining

Types of Data Mining Methods and Marketing

Data mining methods can be divided in multiple ways. However, most books on the topic, and especially those related to marketing and business intelligence, will generally divide data mining methods into two types, the ones related to supervised learning and the ones related to unsupervised learning.

Supervised Learning

Supervised learning is often more associated to scientific research as it includes tasks where the data miner needs to describe or predict the relationship between a set of independent variables (also referred to as inputs, features) and a dependent variable (also referred to as outcome, output or a target variable). Moreover, the dependent variable can be categorical (i.e. churn rate or classes of customers) or continuous (i.e. money earned from that customer) while the independent variables may be of any type but needs to be coded properly (i.e. dividing the categorical variables into separate binary variables). From a marketing and business intelligence perspective, I will divide supervised learning into two interrelated tasks: (1) supervised classification tasks and (2) Predictive Analysis.

Supervised Classification tasks: Supervised classification tasks occurred when you want to predict correctly to which class/category (this is the dependent variable) belong the new observations (i.e. customers) based on results from an already known training dataset. Generally, you will achieve this task by using: (1) a training dataset, (2) a validation dataset and (3) a test dataset. Most known methods I’m using for these tasks are the following:

1. Multinomial Logit (MNL)
2. Linear Discriminant Analysis (LDA)
3. Quadratic Discriminant Analysis (QDA)
4. Flexible Discriminant Analysis with Multivariate Adaptive Regression Splines (FDA – MARS)
5. Penalized Discriminant Analysis (PDA)
6. Mixture Discriminant Analysis (MDA)
7. Naïve Bayes Classifier (NBC)
8. K-Nearest Neighbor (KNN)
9. Support Vector Machines with multiple Kernels (SVM)
10. Classification and Regression Trees (CART)
11. Bagging
12. Boosting
13. Random Forests
14. Neural Networks

Predictive Analysis: I’ve decided to include the expression “Predictive Analysis” here, since it’s a buzzword in the web community nowadays. However, any task related to supervised classification involve a so-called “Predictive Analysis”. However, “Predictive Analysis” is a broader expression that also includes tasks related to the prediction of a continuous dependent variable rather than a categorical variable. Additional methods which can’t be used to conduct classification analyses may be used for predictive analyses with continuous variables and vice-versa.

Unsupervised learning

Unsupervised learning is when the data miner task is to detect patterns based only on independent variables. It is generally presented more from an algorithmic fashion rather than from a purely statistical fashion. Well-known methods applied to marketing includes: (1) Market Basket Analysis and (2) Clustering.

Market Basket Analysis: Market basket analysis (also abbreviated as MBA to confuse you even more) is certainly one of the most known and easier task relating data mining and marketing. It is considered more as a typical marketing application rather than as a data mining method. It can be simplified as a simple Amazon recommendation algorithm showing as an association rule that “the probability that customers who bought item A also bought item B is 56%”. The classic urban legend about Market Basket Analysis is the “beer” and “diapers” association where a large supermarket chain, most people will say Walmart, did a Market Basket Analysis of customers’ buying habits and found an association between beer purchases and diapers purchases. It was theorized that the reason for this was that fathers were stopping off at Walmart to buy diapers for their babies, and since they could no longer go to bars and pubs as often as before, they would buy beer as well. As a result of this finding, the supermarket chain managers have placed the diapers next to the beer in the aisles, resulting in increased sales for both products.

Clustering: The method of Clustering is defined as the assignment of a set of observations (customers) in subsets (clusters) where customers in a cluster are similar to each other while they are different from other customers in other clusters. Clustering is often used in marketing for segmentation tasks. However, even though segmentation may be achieved through “clustering”, more modern supervised methods such as Bayesian Mixture Models, which I must say are not really part of the data mining field, are used by the few practitioners who can actually understand how to program this method (this is one method I am programming these days). For more about segmentation, I would refer anyone to the book “Market Segmentation: Conceptual and Methodological Foundations” by Michel Wedel and Wagner A. Kamakura, both are professors and well-known authorities on the topic.

Some Top References

I must say without a doubt that the best book I know about data mining is surely “Elements of Statistical Learning” by Stanford Professors Trevor Hastie, Robert Tibshirani, and Jerome H. Friedman which covers broadly and nearly every type of methods you can use to conduct data mining tasks. However I must admit that this book has a focus on the statistics behind the methods (but it’s extremely clear) rather than on the software tools (No, it’s not a cookbook) you could use to conduct these analyses, and it may also lack of marketing applications for a marketer. Furthermore, to get some updates about the data mining world, KD Nuggets, administered by Gregory Piatetsky-Shapiro, is actually THE reference for the data mining world.

Some Top Software

Here is a description of some software I would recommend for data mining tasks, feel free to propose your own software in the comments section:

1. R: R is actually my favorite software. I have been using the software for mainly all of my statistics-related tasks for the last 2 years. Its free, open source, it has an extensive and very knowledgeable community, it’s extremely intuitive and it can be learned more easily if you have knowledge of software such as C++, Python and/or GAUSS. Furthermore, there are a lot of useful packages available to facilitate the coding. However, I must say that compared to C++ or SAS, sometimes R can be slow for data mining tasks involving a heavy load of data.

2. rattle: rattle, which stands for the R Analytical Tool To Learn Easily, is a “point and click” data mining interface related to R and developed by Graham Williams of Togaware. Frankly, I must admit that this software rocks even though I generally don’t like “point and click” software. It’s extremely complete and quite easy to use.

3. SAS Enterprise Miner: SAS Enterprise Miner, a module in SAS, was the first software I used for performing data mining tasks. It is extremely fast and user-friendly. However, I must admit that it reminds me software like Amos, now included in PASW (formerly SPSS) for Structural Equation Modeling (SEM) tasks, where you move the “little truck” to build your model and don’t really understand what you’re doing at the end of the day. Furthermore, it costs a lot but to my knowledge, SAS is the only software platform integrating data mining tasks with web analytics and social media analytics.

4. RapidMiner: RapidMiner formerly known as YALE (Yet Another Learning Environment) is considered by multiple data miner as THE software to use to conduct data mining tasks. Similarly to R, the software is open source as well as free of charge for the “Community” version. I haven’t made the switch from R to RapidMiner yet and I am currently testing the software in depth.

5. Salford Systems: I must confess that I never used Salford Systems software but know them by reputation, thus, I can’t have a clear personal opinion on the software. However, statisticians working at Salford Systems are presenting workshops on data mining for the next Joint Statistical Meeting (JSM) in Miami at the end of July 2011 which I might attend.

rattle - Software for Data Mining and Business Intelligence

Waiting time and Conclusion

Whatever the software you’re using, data mining-related tasks will always be demanding in terms of your computer memory. Data Mining in marketing and business intelligence and more broadly KDD is an art that requires strong statistical skills but also a great comprehension of marketing problems. So when you’re waiting for your data mining computations, feel free to come by and read my other cool posts on your other computer! In anyways, enjoy data mining and as one of my friend would say “show some respect to the machine”, but even more to the data miner!

Cheers,

Jean-Francois Belisle

Share/Save

Each time you’re visiting a new city, a hi-tech or a non hi-tech city, if you’re a sports fan, what are you asking for before visiting the city? Your question might look like: So what is the best sports show in this city? People in New York City will tell you to attend a New York Yankees MLB (Major League Baseball) game while people in Montreal will tell you to attend a Montreal Canadiens NHL game. In most American cities, the sport of hockey ranks low in terms of popularity and brand awareness, and comes generally after (1) Football, (2) Basketball and (3) Baseball. In many American cities, the hockey team has a brand that is lower on awareness than any NCAA (National Collegiate Athletic Association) team for the three aforementioned sports. The situation is reversed in all Canadian cities were hockey is the number 1 sport. The Bettman’s era (1993 to now) has done a lot to increase the awareness of hockey and the NHL in the US even though it still remains low. However, low brand awareness of its teams isn’t great for the NHL brand for sure, but low brand awareness added to decreasing reputation is even worse. During the past few years, every time a player received a concussion diagnostic, journalists and fans kept adding more and more negative thoughts to the table, claiming that suspensions or the game itself should be rethink. In the last week, as most of you have certainly seen, the Chara/Pacioretty incident hasn’t helped the reputation of the league at all. The incident was simply the culmination of a series of violent events were the league has been lenient. Thus, it doesn’t really take an Einstein brain to detect that there is a brand crisis hitting (or bone-crushing) the NHL these days. By the way my colleague and friend Bob Mackalski wrote a great post on the topic entitled “The unCanadian values of the NHL and Zdeno Chara” (in fact his post is a great complement of mine and vice versa). Here is the recap of the events of the last week that helped to propagate the brand crisis, instead of stopping it:

Tuesday March 8th – Zdeno Chara hits Max Pacioretty, the latter one left the game on a stretcher;
Wednesday March 9th – Max Paccioretty injury diagnostic includes a heavy concussion and a cracked neck vertebra;
Wednesday March 9th – Mike Murphy announced there is no suspension for Chara’s hit;
Friday March 11th – Gary Bettman’s contract was extended for 5 years.

The Chara/Pacioretty incident by itself is damaging the brand for sure, but the reaction of the league, as well as the announcement of Gary Bettman’s renewal is damaging the brand reputation even more. Someone’s got to take the blame, someone’s got to apologize for sure, the Montreal Canadiens organization also needs to do something since the boards stanchion that caused a part of the injury is in the Bell Center. Propositions should be put forward and prioritized. If there was a crisis for a firm operating in a competitive market and the PR professionals would have acted the way the NHL has acted, they would have been fired on the spot. Using simple free online brand monitoring sentiment analysis analytical tools (that you can also use for your own purposes) such as Tweetfeel (see Figure 1) and Twendz (see Figure 2), are indicators of a brand in need of help. These results also corroborate with the ones available on Google Insights for Search (see Figure 3). All analysis were conducted on Sunday March 13th 2011.

Figure 1 - Tweetfeel Analytics and NHL

According to Tweetfeel, 33% of tweets on Twitter related to the NHL were positive, even without comparison basis, its hard to conclude that these results are great news.

Figure 2 - Twendz Analytics and NHL

According to Twendz, 52% of the tweets that were classified as either positive or negative (23/44), were negative. That is still low.

Figure 3 - Google Insights for Search Analytics and NHL

According to Google Insights for Search, for the March 5th to March 11th period, there is a breakout (an increase of more than 100%) in Google’s search queries for everything related to the Chara hit (Chara, Chara hit, nhl hit) in the US, not in Canada. I would especially highlight the negative branded search query “nhl hit”.

Brand Values of the Hockey Game

The old brand values of the NHL were the following: “patriotism”, “team spirit”, “respect”, “exciting plays”, and “hard work”. Nowadays, the words that are put forward are: “Fast-paced game”, “exciting plays” and “bone-crushing hits”. Simply look at a typical NHL video game to easily understand what the values of today’s NHL are. At the end of the day, its humans playing against other humans and these humans have families, not like in video games where AI (Artificial Intelligence) is in charge of everything.

Brand Values of Teams

Each team have different history and different brand values, these values may be dictated by history, the owner or the type of players forming the actual team. I remember when I went to see Game 4 of the second round of the NHL playoffs in Philadelphia in 2008, when the Montreal Canadiens eventually lost to the Philadelphia Flyers in 5 games. I was awfully surprised to see that the tagline of the Philadelphia Flyers playoff round was “Vengeance now” where “bone-crushing” illegal hits that eventually caused suspensions were shown on the huge screen as well as the altercations between Ron Hextall and Chris Chelios. I am not praising for no hits and no fights, I am simply praising for common sense and respect.

Brand Values of Sponsors

Does it fit? There is the question that should always be brought forward by any brand who is planning to sponsor a NHL event. Does the values of my brand fits with the values of the NHL? Does the values of my brand fits with the values of the team I am sponsoring? If the answer is “yes”, then you know what you can do. If the answer is “no”, do like Air Canada and Via Rail.

Values of Fans

Fans are the ones buying tickets. I would be surprised that watching players getting out of the game on a stretcher is what they want to see. I would be surprised that when law firms or accounting firms are giving hockey tickets to bank employees they promote the hockey game by saying that maybe they’ll have the opportunity of seeing a player getting out of the game on a stretcher.

The Structure of the Market and Incentives

No other hockey league is competing directly against the NHL in North America. It’s a monopoly, no one is offering the same services at the same level, the only other international competitor is the KHL (Kontinental Hockey League), which is based in Russia and mostly consists of Russian players. Thus, if the NHL takes a bad decision or is poorly managed in terms of game suspensions, it’s quite hard to measure how it performs compared to a competitor, since there is no direct competitor! At the end of the day, like in any monopoly, a number of fans who loved the game are taken for granted.

Image of the KHL featuring Alexei Yashin and Jaromir Jagr

To Destabilize You

Before concluding this post, I simply would like to congratulate Vancouver Canucks backup goaltender Cory Schneider for being the first NHL goaltender to score a hat-trick in a hockey game (see below).

According to Sportsnet, Cory Schneider became the first NHL Goalie to score a hat-trick

Conclusion

In conclusion, the NHL is like an Arabic government, it’s a monopoly and it can be dictatorial at times, the only thing that can change mentalities is through a revolution, a revolution that needs to be more organized and more disciplined compared to what we have seen so far.

Jean-Francois Belisle

Share/Save

Web Analysts are mostly men and generally men like curves and women, so now you partially understand part of the purpose of the title, for the other portion simply read the rest of the blog post. The job of a web analyst lays in-between three fields: (1) information systems, (2) marketing, and (3) statistics. Concerning my expertise, my strengths lays mostly on the last two components, since I have strong expertise in both marketing (doctoral-level + consulting) and statistics (doctoral-level + consulting). But mostly, I have strong training in thinking or if you prefer, as it was founded by Aristotle, in “logic”; actually for most of my life I have been paid to think, and more importantly, I have been paid to “think” to thereafter “act”, and I have acted too. Thus, based on the principle of “logic”, I have decided to write this post about one simple concept that is useful for web analytics purposes, the statistic principle of “smoothing”. I have decided to apply it to a “web analytics” context but I could also have easily applied it to multiple other contexts.

An Hypothetical (but Realistic) Scenario

Let’s take the evolution of a time-series representing the number of conversions on a website at the week-level. For the purpose of this example, I will refer to this conversion as a purchase, where the number of purchases is positively bounded between 0 and a finite number “S”. I decided to focus on the number of conversions instead of the conversion rate, since for most companies, what is most important from a financial perspective, are “absolute values” rather than “percentage values”. Let’s imagine you’re in charge of reporting this metric in a KPI fashion and to interpret. Here is below the graph and its associated table you have in front of you.

Figure 1 - Evolution of Purchase Over Time

So what would you do? Let’s say that you know there is nothing going wrong with observation 12 and don’t want to report a false alert (or a false alarm as they would say in “control engineering“) and therefore don’t want to alert anyone in the organization. You know that the only reason why observation 11 in Figure 1 is high is because of a short small offline advertising campaign that is quite hard to track (nobody listen to you when it comes to offline campaign, arghhh!). One last point, the crazy HiPPO in your organization wants “purchase” reported in a KPI fashion for sure, so you can’t escape from this hazardous task. So what would you clearly do fellow?

Which metric is the best?

1) Report the growth rate as a KPI? This would make (58-90)/90 = – 35.56%, this would create for sure an alert, which is a false alert as you already know it.
2) Draw a trend between the first period and the period before the last period and compare? (178-90)/12 = 7.33, 58/(100-7.33)) – 1 = – 29.84%, this would do the same thing as in 1) and would statistically suck anyway.
3) Do some eyeball regression? This would be excellent, since it would clearly identify that observation 11 was a special case, and that the first 4 observations were high because of Holidays. The problem is that you’re paid to report numbers, so where are the numbers fellow?
4) Do some basic smoothing?
Case 1 – Compare to a moving-average of order 3: (58 / ((90+68+54)/3)) -1 = -17.92%, still a drop but less.
Case 2 – Compare to a moving-average of order 4 or 5: (58 / ((90+68+54+58)/4)) -1 = -14.07%, still a drop but that’s better, you can stop to sweat a little.
Case 3 – Compare to a weighted-moving average of order 4 with the current weights (t-1 = 50%, t-2 = 25%. t-3 = 12.5%, t-4 = 12.5%) – (58 / (90*.5+68*.25+54*.125+58*.125))-1 = -28.40%, that’s quite a stupid approach since your objective is not to create a false alert buddy.
Case 4: Compare to a moving-average of order 3 by eliminating observation 11: 58/((58+54+68)/3)-1 = -3.33%, that’s the kind of results you want to show, but you eliminate one observation and it may look a little too optimistic.

In conclusion, the case 2 in the smoothing part in 4) would be my humble choice and should be favored compared to the growth ratio reported in 1). Furthermore, don’t forget that you need to present this KPI along with other KPIs in your analysis.

Historical Background on Smoothing and Moving Averages

No, smoothing is not the verb associated to the art of making “smoothies” as you have noticed. Smoothing is an exploratory tool that is used to approximate a function that attempts to capture important patterns in the data (the chapter 7 of the famous American statistician John W. Tukey book entitled “Exploratory Data Analysis” published in 1977 gives a great overview on the topic). Moving averages introduced in the previous paragraph, which are certainly the most known and simplest kind of smoothing method, date back to the seminal work of Scottish statistican Udny Yule at the beginning of the twentieth century (Yule 1909) citing English statistician Reginald Hooker (Hooker 1901). As shown in the calculations, moving averages involves to smooth a curve by assigning weight to neighbored previous observations, in this case for predicting a new observation and comparing to the actual observation to create a marvelous KPI. When I was teaching “Strategic Marketing” at HEC Montréal, I must admit I always wondered why we were teaching moving averages, since most time-series we were using at the time were mostly monthly and quarterly time series, smoothing mostly gave bad results. I thought I was only teaching these methods because they were on the curriculum, not because I thought they were actually useful. However, in web analytics, with data available at the day-level (and if we want, we can even dig deeper at the hour-level and minute-level), even though there is a lot to learn from variations, sometimes we also need to smooth those variations using smoothing methods such as moving averages or even more advanced methods which I may write about it if there is interest.

Exploratory Data Analysis , Smoothing & Smoothies

Conclusion

KPIs related to growth rate sometimes give erroneous results and smoothing methods such as moving averages may be useful. Enjoy logical web analytics, but also, enjoy the sexy smoothing curves (as previously discussed) while drinking smoothies!

Cheers,

JF

Some References, which I think maybe Useful

Hooker, Reginald H. (1901) “Correlation of the Marriage-Rate with Trade,” Journal of the Royal
Statistical Society, 64 (3), 485-492.

Tukey, John W. (1977). Exploratory Data Analysis, Addison-Wesley, Reading.

Yule, G. Udny (1909) “The Applications of the Method of Correlation to Social and Economic,” Journal
of the Royal Statistical Society, 72 (4), 721-730.

Share/Save