Course description: InfoSphere Warehouse 9 - Data Mining and Unstructured Text Analysis - WBT

Note: This is a self-paced online course. This course usually requires 16 hours to complete. Once you receive your access information, you will have access to this course for 1 year.

Please do not make travel arrangements for this course. After you receive confirmation that you are enrolled, you will be sent further instructions to access the course materials.

This course is a subset of the course InfoSphere Warehouse 9 Components (DW352). It is designed to give an in-depth knowledge of the data mining and unstructured text analysis components of InfoSphere Warehouse. You will first be given a foundation in data mining. Then learn about the various types of data mining algorithms supported by InfoSphere Warehouses. Exercises will allow you to create mining flows that invoke the various mining algorithms. Much data resides in data warehouses in free-form text. Unstructured text analysis allows you to create dictionaries and extract relevant data from the text fields that can then be used to enhance a data mining run or to possibly add additional dimensions to a star schema. This course is is appropriate for those who are using InfoSphere Warehouse within the IBM Smart Analytics system and for those that are using IBM InfoSphere Warehouse independently.

Course Materials

The course materials address InfoSphere Warehouse 9.7.

Hands-On Labs

Five labs are included to address InfoSphere Warehouse 9.7.

Training Path

This course is part of an IBM Training Path. Taking this course in the recommended sequence allows you to maximize the benefits from your education.

View this course in other countries

Back to top

IBM Education Advantage Program Eligibility

• Yes - IBM Education Pack - Online account

Back to top

This advanced course is for those who will be using the data mining and unstructured text analysis components of IBM InfoSphere Warehouse or IBM InfoSphere Warehouse on System z.

This course is also appropriate for customers who have acquired the IBM Smart Analytics System.

Back to top

It is strongly suggested you'll be familiar with DB2 and have attended InfoSphere Warehouse 9 - SQL Warehouse Tool and Administration Console (DWA52). Attendance in Infosphere Warehouse 9 - Cubing Services (DWB52) would be a benefit, but is not required

Back to top

• Describe the different data mining algorithms supported by InfoSphere Intelligent Miner
• Create mining flows that will create data mining models and score those models against new data
• Extract data from an unstructured text field in order to enhance a data mining run or create additional dimensions for a star schema

Back to top

A Data Mining Foundation

• Define data mining
• Distinguish between verification-driven and discovery-driven analysis
• Discuss where data mining can be applied
• Describe the key elements for a successful data mining project
• Describe the purposes and uses of a data mining process
• State six steps in a data mining process  

An Introduction to InfoSphere Intelligent Miner

• Describe the components of InfoSphere Intelligent Miner
• List the different model types supported by InfoSphere Intelligent Miner Modeling
• Describe how InfoSphere Intelligent Miner Scoring is used
• Explain how to inspect your data using different distributions: Univariate, Bivariate, and Multivariate
• Describe how to execute a mining flow
• Discuss how to generate a Java class from a mining flow

InfoSphere Intelligent Miner Supported Mining Techniques

• Describe the Cluster function used in InfoSphere Intelligent Miner Modeling
• Describe the Classification function used in InfoSphere Intelligent Miner Modeling
• Describe the Regression function used in InfoSphere Intelligent Miner Modeling
• Describe the Associations function used in InfoSphere Intelligent Miner Modeling
• Describe the Sequential Rule function used in InfoSphere Intelligent Miner modeling
• Describe the Time Series function used in InfoSphere Intelligent Miner modeling

Unstructured Text Analytics

• Describe the regular expression extraction capabilities of InfoSphere Warehouse
• Describe how the frequent terms analysis capabilities of the Design Studio can aid in creating a dictionary
• Describe how list base information extraction can be used to enhance a data mining run

Agenda

• Welcome
• Unit 1: A Data Mining Foundation
• Unit 2: An Introduction to InfoSphere Intelligent Miner
• Unit 3 - InfoSphere Intelligent Miner Supported Mining Techniques
• Topic 1: Clustering Functions
• Exercise for Clustering
• Topic 2: Predictive Models
• Unit 3:InfoSphere Intelligent Miner Supported Mining Techniques
• (Continued)
• Exercise for Prediction
• Topic 3: Associations and Sequential Rule
• Exercise for Associations and Sequential Rule
• Unit 4: Unstructured Text Analysiscise for Unstructured Text Analysis

Back to top

HW/SW CONFIGURATION

The minimum hardware and software required to launch the course are:

• Reliable HIGH-SPEED INTERNET connection (min 200 kbps up and down)
• Windows 2000 or XP or Vista
• Computer with soundcard
• Headset or computer speakers
• Internet Explorer 5.01 or later, or Firefox 1.0 or later

Network Speed Test

http://clpext.moppssc.com/index.php?option=com_wrapper&view=wrapper&Itemid=8

User: clp

Pass: ibmeduc

For example, a speed test against the server with a slow connection of 140 Kbps download and 28 Kbps upload took 14 minutes to load a 30min recording before the video began. Extrapolate from this result to estimate approximately how fast your network internet access would be.

High-speed broadband internet access is the recommended configuration for this course.

Keyboard Configuration

If you use a different character keyboard, you may experience errors when entering passwords. If possible, change your language/country settings for your keyboard to USA, which allows you to enter characters as in a QWERTY keyboard.

Back to top