Schedules:

There are currently no scheduled classes for this course.

 
  Data Mining with SQL Server 2005
 

3-Day (BI-DMNNG05-401-EN)

Description
Audience
Prerequisites
Course Objectives
Course Outline
Course Materials

Description

In this course attendees learn how to use Data Mining to find advanced patterns in their data and perform predictions based on the patterns found using SQL Server 2005 Analysis Services. After the course, you will be able to:

  • Describe what Data Mining is and what business questions can it answer
  • Explain the process of a Data Mining project
  • Explore and understand your data using descriptive statistics, OLAP cubes, reports and other tools
  • Prepare the data to make better models
  • Understand the Data Mining algorithms, and when to use them
  • Create Data Mining Models and browse them
  • Evaluate models to find the one that gives best results
  • Use SQL Server 2005 Integration Services Data Mining tasks
  • Do Text Mining with Integration Services
  • Understand and use the Data Mining Extensions (DMX)language
  • Deploy Data Mining models in production using custom application, OLAP cubes or reports developed with SQL Server 2005 Reporting Services

Audience

This course is intended for business intelligence application developers and advanced administrators.

Prerequisites

The attendees should have at least moderate experience with data warehousing, reporting and On-Line Analytical Processing. The attendees should be familiar with the Transact-SQL language. Knowledge of a .NET language like C# or VB.NET is welcome as well.

Course Objectives

On course completion you will be able to:

  • Describe what Data Mining is and what business questions can it answer
  • Explain the process of a Data Mining project
  • Explore and understand your data using descriptive statistics, OLAP cubes, reports and other tools
  • Prepare the data to make better models
  • Understand the Data Mining algorithms, and when to use them
  • Create Data mining Models and browse them
  • Evaluate models to find the one that gives best results
  • Use SQL Server 2005 Integration Services Data Mining tasks
  • Do Text Mining with Integration Services
  • Understand and use the Data Mining Extensions (DMX) language
  • Deploy Data Mining models in production using custom application, OLAP cubes or reports developed with SQL Server 2005 Reporting Services

Course Outline

Module 1: Introduction to Data Mining

  • Introduction
  • Business Questions
  • Process
  • Tools

Module 2: Understanding and Preparing the data

  • Using OLAP cubes and reports
  • Derived variables
  • Missing values and outliers
  • Descriptive statistics
  • Information theory
  • Sampling and confidence

Module 3: Data Mining Algorithms Part 1

  • Naïve Bayes
  • Decision Trees
  • Neural Networks
  • Linear Regression
  • Logistic Regression

Module 4: Data Mining Algorithms Part 2

  • Clustering
  • Sequence Clustering
  • Association Rules
  • Time Series

Module 5: Using Integration Services with Data Mining

  • Data Mining tasks
  • Data Mining transforms
  • Data Mining preparation
  • Text Mining

Module 6: DMX Language

  • DDL statements
  • DML statement
  • DMX Select
  • Advanced examples

Module 7: Integrating Data Mining in BI applications

  • Preparing Data Mining reports with Reporting Services
  • Integrating with OLAP cubes

Module 8: Developing Data Mining Applications

  • XMLA
  • Developing models with AMO
  • Building intelligent applications using ADOMD.NET Client
  • Client browsers
  • Server stored procedures with ADOMD.NET Server

Module 9: Managing and Maintaining Data Mining models

  • Deployment
  • Backing up and restoring
  • Security

Course Materials

  • Printed student manual (in English)
  • Student CD with exercises, labs and supporting materials

The following software is used during the workshop:

  • MS SQL Server 2005 Developer Edition
  • MS Visual Studio .NET 2005 Professional