Data mining makes analytical business applications, such as CRM, smarter by providing insight thatgoes beyond just the obvious knowledge. By making your applications smarter, data miningtrans- lates into a higher return onyour warehouse investment. (See Figure 1). The Difference betweenOLAP and Data MiningA commonly asked question is “What is the difference betweendatamining and on-line analytical processing (OLAP)?” OLAP is a business intelligence tool thatallows you to analyze and understandparticular business drivers. Typically, a specific descriptive or factual questionis formulated and either validated orrefuted through ad hoc queries. OLAP results are factual results. For example, you may ask, “How many size 7 shoes did I sell in the past three months?” The results are factual answers thatenable you to validate your hypothesis or order decision. But what happens if you have hundreds of variables toanalyze? It becomes difficult to formu- late a good hypothesis or relationship among your data. In addition, OLAP tools don’tproduce predictive orestimated values with associated accuracy expectations. Data mining, on the other hand, is a form of discovery driven analysis where statisti- cal and machinelearning techniques are used to make predictions or estimates about outcomes or traits before knowingtheir true values. Data miningtechniques are used to find meaningful, often com- plex, andpreviously unknown patterns in data. For example, you may ask, “How manysize 7 shoes should I order for the next season?” Data miningtechniques can be used to buildmodels based on detail data to predictthe number of size 7 shoes soldwithina given time period. Typically, OLAP analyses use predefined, summa- rized or aggregated data, suchas multi-dimensional cubes, where data mining requires detail data that is aggre- gated to optimal levels andanalyzed at the individual record level.Although these technologies are used for different purposes, OLAP anddata mining are complementary. During the data mining explorationphase, you may PAGE 4 OF 15
DataMining Primeruse OLAP technology to help you under- stand your data. Data miningresults can also be used in OLAP applications by incorporating new predictive variables or scores as dimensions or attributes in your OLAPtool. For example, if you calculate a new predictive variable called “Customer Value” thatcharacterizes the value of a customerto your business in terms of profitability, you can include this new variable as an attribute in your OLAP tool. When retailers analyze which prod- ucts to stock, they can consider products that attracthigh-value or profitable customers. (See Figure 2). How Does Data Mining Work? Data mining leverages artificial intelli- gence and statistical techniques to build models. Data mining models are built fromsituations where you know the outcome. These models are thenapplied to other situations where you don’tknow the outcome. Forexample,if your data warehouse identifies customers who have
You've reached the end of your free preview.
Want to read all 15 pages?
- Fall '19
- Data Mining, Data Warehouse Professional