Data mining using SQL SERVER 2005 My name

Data mining using SQL SERVER 2005 My name: ZULFIQAR SYED n Holds BSEE from Illinois Institute of Technology. n MCP in ASP. net (C#) n SQL SERVER, ASP. NET, C#, DATA MINING, ANALYSIS SERVICES. n CONTACT: ZULFIQARSYED@YAHOO. COM n HTTP: //ZULFIQAR. TYPEPAD. COM n

Today, we will go over… n Introduction to data mining. What? ? n Why? ? n How? ? n n Data mining demo. Create Model n Train Model n Test Model n Analyze and make predictions. n

Prerequisites for data mining SQL SERVER n T-SQL n

What is Data mining? ? The process of analyzing data to identify patterns or relationships. n Searching large volumes of data looking for patterns that accurately predict behavior in customers and prospects. n

Why Data mining? ? n n Production of very large amount of data. Affordable Computing power. Realization that customer information is one of the key assets. Commercial data mining software readily available.

What does data mining do? Explore data n Discover patterns or rules. n Make Analysis or Predictions. n

Basics of data mining? ? 1. 2. 3. 4. Create mining model based on an algorithm. Train model by passing historical data. Newly trained model contains data patterns. Analyze or make predictions on new data by using it against the trained model.

Demonstration n Demo on data mining.

Demonstration recap. Used Integration Services to create the “test” and “train” data. n Created the model and trained it using train data. n Evaluated different models using test data. n Created report using reporting services. n Managed different projects from the same solution. n

CREATE MINING MODEL [name] ( [column name] [data type] [content type] [usage] …. ) USING Microsoft_Decision_Trees ( <parameters, param list, > )

CREATE MINING MODEL EXAMPLE CREATE MINING MODEL [DTSAMPLE] ( Customer. Key LONG KEY, Gender TEXT DISCRETE, [Number Cars Owned] LONG DISCRETE, [Bike Buyer] LONG DISCRETE PREDICT ) Using Microsoft_Decision_Trees(optional parameters. . )

Q and A n Books n n n Please fill out the evaluation form. n n n Data mining Techniques (Berry/Linoff) Data mining with Sql Server 2005. (Tang/Mac. Lennan) NAME: ZULFIQAR SYED SESSION: Data mining using SQL Server 2005 My contact information: n n ZULFIQARSYED@YAHOO. COM Web log: HTTP: //ZULFIQAR. TYPEPAD. COM These slides will be posted on my web log.