<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	xmlns:georss="http://www.georss.org/georss" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:media="http://search.yahoo.com/mrss/"
	>

<channel>
	<title>Dylan&#039;s BI Study Notes</title>
	<atom:link href="https://dylanwan.wordpress.com/feed/" rel="self" type="application/rss+xml" />
	<link>https://dylanwan.wordpress.com</link>
	<description>My notes about Business Intelligence, Data Warehousing, OLAP, and Master Data Management</description>
	<lastBuildDate>Wed, 20 Mar 2024 12:38:17 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
<site xmlns="com-wordpress:feed-additions:1">437134</site><cloud domain='dylanwan.wordpress.com' port='80' path='/?rsscloud=notify' registerProcedure='' protocol='http-post' />
<image>
		<url>https://s0.wp.com/i/buttonw-com.png</url>
		<title>Dylan&#039;s BI Study Notes</title>
		<link>https://dylanwan.wordpress.com</link>
	</image>
	<atom:link rel="search" type="application/opensearchdescription+xml" href="https://dylanwan.wordpress.com/osd.xml" title="Dylan&#039;s BI Study Notes" />
	<atom:link rel='hub' href='https://dylanwan.wordpress.com/?pushpress=hub'/>
	<item>
		<title>Predictive Analytics and AI/ML</title>
		<link>https://dylanwan.wordpress.com/2024/02/25/predictive-analytics-and-ai-ml/</link>
					<comments>https://dylanwan.wordpress.com/2024/02/25/predictive-analytics-and-ai-ml/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Sun, 25 Feb 2024 22:24:01 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Incorta]]></category>
		<category><![CDATA[Advanced Analytics]]></category>
		<category><![CDATA[ai]]></category>
		<category><![CDATA[artificial-intelligence]]></category>
		<category><![CDATA[Data Science]]></category>
		<category><![CDATA[data-analytics]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2751</guid>

					<description><![CDATA[We have heard about advanced analytics, which was described by dividing analytics into three main types: While many articles explore these concepts,, such as Prescriptive vs. Predictive Analytics: Examples &#38; Use Cases I aim to approach these categories from the standpoint of a software vendor, describe how these categories relate to machine learning practices. The [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2024/02/25/predictive-analytics-and-ai-ml/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2751</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Semantic Layer for Data Scientist</title>
		<link>https://dylanwan.wordpress.com/2022/06/16/semantic-layer-for-data-scientist/</link>
					<comments>https://dylanwan.wordpress.com/2022/06/16/semantic-layer-for-data-scientist/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Thu, 16 Jun 2022 23:36:25 +0000</pubDate>
				<category><![CDATA[BI]]></category>
		<category><![CDATA[Data Science]]></category>
		<category><![CDATA[Incorta]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2731</guid>

					<description><![CDATA[I recently read a good buyer&#8217;s guide from AtScale: The Buyer’s Guide to the Best Semantic Layer Tools for Data and Analytics. I think the buyer&#8217;s guide is fair not because that the company I worked for also has such semantic layer, but I really feel that the drawback of the vendor specific semantic layer [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2022/06/16/semantic-layer-for-data-scientist/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2731</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Cloud Database and Cloud DataLake</title>
		<link>https://dylanwan.wordpress.com/2022/06/15/cloud-database-and-cloud-datalake/</link>
					<comments>https://dylanwan.wordpress.com/2022/06/15/cloud-database-and-cloud-datalake/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 15 Jun 2022 18:54:22 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Cloud Database]]></category>
		<category><![CDATA[Cloud DataLake]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2727</guid>

					<description><![CDATA[The term DataLake was invented to describe the data storage and the fact that after Hadoop and HDFS were introduced, you can have a cheaper way and place to store your data without using a traditional database, by traditional, I mean a RDBMS, relational database management system. Cheaper is not just about cost, it is [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2022/06/15/cloud-database-and-cloud-datalake/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2727</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>ML Data Engineering and Feature Store</title>
		<link>https://dylanwan.wordpress.com/2022/03/22/ml-data-engineering-and-feature-store/</link>
					<comments>https://dylanwan.wordpress.com/2022/03/22/ml-data-engineering-and-feature-store/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Tue, 22 Mar 2022 17:23:34 +0000</pubDate>
				<category><![CDATA[ML]]></category>
		<category><![CDATA[feature store]]></category>
		<category><![CDATA[ML feature]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2722</guid>

					<description><![CDATA[A typical ML process flow is about Load the data Explore and Clean the data Create features Create ML model Deploy the ML model for inference/prediction The problem of this flow is that it ignores the fact that the process has to be repeatable and the data need to be reused. In the real world, [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2022/03/22/ml-data-engineering-and-feature-store/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2722</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Getting Data into Cloud</title>
		<link>https://dylanwan.wordpress.com/2021/08/27/getting-data-into-cloud/</link>
					<comments>https://dylanwan.wordpress.com/2021/08/27/getting-data-into-cloud/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Fri, 27 Aug 2021 19:51:10 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2716</guid>

					<description><![CDATA[When I worked on the data warehousing technologies, we extract the data from the source. The &#8220;Extract&#8221; is the first step in ETL (or ELT). The extraction was typically done by using SQL connection to the database that holds the transactional data. When we start introducing cloud based storage, or the Data Lake, many of [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2021/08/27/getting-data-into-cloud/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2716</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Time Series</title>
		<link>https://dylanwan.wordpress.com/2021/03/12/time-series/</link>
					<comments>https://dylanwan.wordpress.com/2021/03/12/time-series/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Sat, 13 Mar 2021 02:42:18 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Incorta]]></category>
		<category><![CDATA[pandas]]></category>
		<category><![CDATA[pyspark]]></category>
		<category><![CDATA[times series]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2700</guid>

					<description><![CDATA[Times Series is defined as a series of data, typically values of a variables, the value of which may change over time. A set of statistical methods were developed for analyzing such data. Those methods help to understand and interpret the data, and once the data can be understood, then the model can be used [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2021/03/12/time-series/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2700</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Migrating from OBI to Incorta</title>
		<link>https://dylanwan.wordpress.com/2020/12/09/migrating-from-obi-to-incorta/</link>
					<comments>https://dylanwan.wordpress.com/2020/12/09/migrating-from-obi-to-incorta/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 09 Dec 2020 17:50:56 +0000</pubDate>
				<category><![CDATA[BI]]></category>
		<category><![CDATA[BI Application]]></category>
		<category><![CDATA[DBI]]></category>
		<category><![CDATA[EBS]]></category>
		<category><![CDATA[Incorta]]></category>
		<category><![CDATA[Infomatica]]></category>
		<category><![CDATA[OBIA]]></category>
		<category><![CDATA[OBIEE]]></category>
		<category><![CDATA[Oracle]]></category>
		<category><![CDATA[Oracle BI Suite EE]]></category>
		<category><![CDATA[OTBI]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2690</guid>

					<description><![CDATA[I am sharing my experience of migrating from OBI to Incorta. Process Start with Incorta EBS Blueprint Configure and customize for the deploying company Optionally, Demo the Fusion Connector Preview and demo to business users using their own data Provide the existing OBI dashboard usage analysis &#8211; Help prioritize the replacement project Provide the lineage [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2020/12/09/migrating-from-obi-to-incorta/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2690</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>

		<media:content url="https://dylanwan.wordpress.com/wp-content/uploads/2020/12/comcast_requisition_report_query_plan.png?w=1024" medium="image" />
	</item>
		<item>
		<title>Oracle App Cloud and Incorta</title>
		<link>https://dylanwan.wordpress.com/2020/09/30/oracle-app-cloud-and-incorta/</link>
					<comments>https://dylanwan.wordpress.com/2020/09/30/oracle-app-cloud-and-incorta/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 30 Sep 2020 18:35:57 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[EBS]]></category>
		<category><![CDATA[Human Resource Intelligence]]></category>
		<category><![CDATA[Incorta]]></category>
		<category><![CDATA[Oracle]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2683</guid>

					<description><![CDATA[OTBI is great. But when people are migrating from Oracle EBS to Oracle Cloud App, they would like to view the data from both EBS and Oracle Cloud, Incorta becomes a cost saving and a quick implementation solution without implementing a data warehouse. Incorta is not a data warehouse although it does has the data [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2020/09/30/oracle-app-cloud-and-incorta/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2683</post-id>
		<media:thumbnail url="https://dylanwan.wordpress.com/wp-content/uploads/2020/09/screen-shot-2020-09-30-at-9.41.42-am.png" />
		<media:content url="https://dylanwan.wordpress.com/wp-content/uploads/2020/09/screen-shot-2020-09-30-at-9.41.42-am.png" medium="image">
			<media:title type="html">Screen Shot 2020-09-30 at 9.41.42 AM</media:title>
		</media:content>

		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Scalable Distributed BI Architecture</title>
		<link>https://dylanwan.wordpress.com/2019/11/26/scalable-distributed-bi-architecture/</link>
					<comments>https://dylanwan.wordpress.com/2019/11/26/scalable-distributed-bi-architecture/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 27 Nov 2019 01:15:57 +0000</pubDate>
				<category><![CDATA[BI]]></category>
		<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Incorta]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2675</guid>

					<description><![CDATA[Incorta, a scalable distributed BI system...]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2019/11/26/scalable-distributed-bi-architecture/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2675</post-id>	<georss:point>37.536894 -122.324851</georss:point>
		<geo:lat>37.536894</geo:lat>
		<geo:long>-122.324851</geo:long>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Is ETL still necessary?</title>
		<link>https://dylanwan.wordpress.com/2019/01/22/is-etl-still-necessary/</link>
					<comments>https://dylanwan.wordpress.com/2019/01/22/is-etl-still-necessary/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 23 Jan 2019 05:10:25 +0000</pubDate>
				<category><![CDATA[BI]]></category>
		<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[ETL]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2671</guid>

					<description><![CDATA[ETL stands for Extract, Transform, and Load. Extract and Load, their existence itself implies that the source data and target data are stored separately, so you need to extract from source and load the data into the target data store. Extract and Load won&#8217;t go away if the data used for reporting is not stored [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2019/01/22/is-etl-still-necessary/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2671</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Is Star Schema necessary?</title>
		<link>https://dylanwan.wordpress.com/2019/01/18/is-star-schema-necessary/</link>
					<comments>https://dylanwan.wordpress.com/2019/01/18/is-star-schema-necessary/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Fri, 18 Jan 2019 18:30:37 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2669</guid>

					<description><![CDATA[A star schema describes the data by fact and dimension. From one angle, it is a data modeling technique for designing the data warehouse based on relational database technology.  In the old OLAP world, even though a cube is also links to the dimensions that describe the measure, we typically won&#8217;t call them Star Schema. [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2019/01/18/is-star-schema-necessary/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2669</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Incremental ETL : Streaming via Micro-Batch</title>
		<link>https://dylanwan.wordpress.com/2017/10/11/incremental-etl-streaming-via-micro-batch/</link>
					<comments>https://dylanwan.wordpress.com/2017/10/11/incremental-etl-streaming-via-micro-batch/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Thu, 12 Oct 2017 04:40:03 +0000</pubDate>
				<category><![CDATA[Data Warehouse]]></category>
		<category><![CDATA[ApacheSpark]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2635</guid>

					<description><![CDATA[A modern analytic application takes the approach of streaming data to perform the similar process as the traditional data warehousing incremental ETL. Actually, if we look into Spark Streaming in details, the concept of streaming in Spark and Incremental ETL are the same: Spark Streaming is a Micro-Batch based streaming. Each micro-patch is much like [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/10/11/incremental-etl-streaming-via-micro-batch/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2635</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Incremental ETL &#8211; The last refresh date</title>
		<link>https://dylanwan.wordpress.com/2017/10/11/incremental-etl-the-last-refresh-date/</link>
					<comments>https://dylanwan.wordpress.com/2017/10/11/incremental-etl-the-last-refresh-date/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 11 Oct 2017 20:31:29 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Data Warehouse]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2563</guid>

					<description><![CDATA[There are multiple ways to model the last refresh date. In OBIA, DAC and Informatica based ETL, the last refresh date is maintained within DAC. It is maintained at the level of the source tables that populates the data. Oracle BI DAC User Guide &#62; About Refresh Dates and DAC&#8217;s Incremental Load Strategy In OBIA [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/10/11/incremental-etl-the-last-refresh-date/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2563</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Use Bit to represent groups</title>
		<link>https://dylanwan.wordpress.com/2017/10/11/use-bit-to-represent-groups/</link>
					<comments>https://dylanwan.wordpress.com/2017/10/11/use-bit-to-represent-groups/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 11 Oct 2017 08:17:46 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Data Warehouse]]></category>
		<category><![CDATA[ETL]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2510</guid>

					<description><![CDATA[Here I am providing an alternate approach of supporting group membership in MySQL. It is a common seen requirement that a group may have multiple members and a person may be added to multiple groups.  This many to many relationship is typically modeled in an intersection table. When the group membership is being used as [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/10/11/use-bit-to-represent-groups/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2510</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Schema On Read?</title>
		<link>https://dylanwan.wordpress.com/2017/09/24/schema-on-read/</link>
					<comments>https://dylanwan.wordpress.com/2017/09/24/schema-on-read/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Sun, 24 Sep 2017 12:48:30 +0000</pubDate>
				<category><![CDATA[Big Data]]></category>
		<category><![CDATA[Data Lake]]></category>
		<category><![CDATA[Data Science]]></category>
		<category><![CDATA[Oracle]]></category>
		<category><![CDATA[Data Mining]]></category>
		<category><![CDATA[Data Warehouse]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2482</guid>

					<description><![CDATA[I saw &#8220;create external table &#8221; first in Oracle DBMS 11G. It was created for the purpose of loading data. When Hive was introduced, a lot of data were already created in HDFS. Hive was introduced to provided the SQL interface on these data. Using the external table concept is a nature of the design.  [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/09/24/schema-on-read/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2482</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Preserve Surrogate Key During Upgrade</title>
		<link>https://dylanwan.wordpress.com/2017/09/23/preserve-surrogate-key-during-upgrade/</link>
					<comments>https://dylanwan.wordpress.com/2017/09/23/preserve-surrogate-key-during-upgrade/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Sat, 23 Sep 2017 12:00:05 +0000</pubDate>
				<category><![CDATA[Data Warehouse]]></category>
		<category><![CDATA[ETL]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2405</guid>

					<description><![CDATA[The generated surrogate key is used everywhere in the data warehouse.  What do we do during upgrade? Here are some approaches: 1. Full Refresh You can perform a full refresh of the data warehouse.  The surrogate keys will be regenerated.  The FK will be updated. Obviously, this is not a good approach.  There are problems [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/09/23/preserve-surrogate-key-during-upgrade/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2405</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Unified Data Model or Not</title>
		<link>https://dylanwan.wordpress.com/2017/09/13/unified-data-model-or-not/</link>
					<comments>https://dylanwan.wordpress.com/2017/09/13/unified-data-model-or-not/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 13 Sep 2017 22:07:54 +0000</pubDate>
				<category><![CDATA[CDH]]></category>
		<category><![CDATA[EDW]]></category>
		<category><![CDATA[Master Data Management]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2377</guid>

					<description><![CDATA[Do we need to store the data all together in same places? Do we need to use the same data model ? Do we need to put data into cloud? Storing the data into a central place is not necessary, as nowadays, I do not really know where the data are stored.  If we talk [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/09/13/unified-data-model-or-not/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2377</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>How to &#8211; Incremental ETL</title>
		<link>https://dylanwan.wordpress.com/2017/09/06/how-to-incremental-etl/</link>
					<comments>https://dylanwan.wordpress.com/2017/09/06/how-to-incremental-etl/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Wed, 06 Sep 2017 18:11:59 +0000</pubDate>
				<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Data Warehouse]]></category>
		<category><![CDATA[ETL]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2363</guid>

					<description><![CDATA[This is a very basic topic.  An ETL 101 question come up a lot in interview. Even we are moving to a different storage and different processing framework, the concepts are still important. The idea is simple &#8211; you do not need to keep extracting and updating all data in the data store that are [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/09/06/how-to-incremental-etl/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2363</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Use Surrogate Key in Data Warehouse</title>
		<link>https://dylanwan.wordpress.com/2017/08/31/use-surrogate-key-in-data-warehouse/</link>
					<comments>https://dylanwan.wordpress.com/2017/08/31/use-surrogate-key-in-data-warehouse/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Thu, 31 Aug 2017 12:46:55 +0000</pubDate>
				<category><![CDATA[BI]]></category>
		<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Data Warehouse]]></category>
		<category><![CDATA[ETL]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2300</guid>

					<description><![CDATA[Using surrogate key is part of dimensional modeling technique for populating a data warehouse using a relational database. The original idea was to generate the sequence generated IDs and use them in between the fact and dimension table, so we can avoid using the concatenated string or using composite key to join.  Also, due to [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/08/31/use-surrogate-key-in-data-warehouse/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2300</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
		<item>
		<title>Prebuilt BI Contents should replace BI Tools</title>
		<link>https://dylanwan.wordpress.com/2017/08/13/prebuilt-bi-contents-should-replace-the-bi-tools/</link>
					<comments>https://dylanwan.wordpress.com/2017/08/13/prebuilt-bi-contents-should-replace-the-bi-tools/#respond</comments>
		
		<dc:creator><![CDATA[Dylan Wan]]></dc:creator>
		<pubDate>Sun, 13 Aug 2017 14:03:27 +0000</pubDate>
				<category><![CDATA[BI]]></category>
		<category><![CDATA[BI Application]]></category>
		<category><![CDATA[Business Intelligence]]></category>
		<category><![CDATA[Prebuilt content]]></category>
		<guid isPermaLink="false">http://dylanwan.wordpress.com/?p=2266</guid>

					<description><![CDATA[Most school districts need the same kind of reports and dashboard for measuring the performance of students, teachers, and schools.   They do not really need to have IT to build reports for them if the vendors can provide the reports OOTB. There is really hardly a need to have a custom reporting tool for building [&#8230;]]]></description>
		
					<wfw:commentRss>https://dylanwan.wordpress.com/2017/08/13/prebuilt-bi-contents-should-replace-the-bi-tools/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">2266</post-id>
		<media:content url="https://2.gravatar.com/avatar/e13d6aa2456d0b8999ef0e0455c02dfcb82a43b2de45b7de9e2111156d4190e4?s=96&#38;d=https%3A%2F%2Fs0.wp.com%2Fi%2Fmu.gif&#38;r=G" medium="image">
			<media:title type="html">Dylan</media:title>
		</media:content>
	</item>
	</channel>
</rss>
