IBM SPSS Modeler Web Mining

Data mining is a proven technology for advanced analysis that detects key patterns and trends. But the time-consuming complexity of preparing Web data with the business context necessary for data mining has hampered its use in Web analysis—until now.

The new standard in Web analysis

IBM SPSS Modeler Web Mining is an add-on module that makes it easy for analysts to perform ad hoc predictive Web analysis within IBM SPSS Modeler’s intuitive visual workflow interface. By bringing together the leading technologies for both Web analytics and data mining—along with more than 40 years of analytical experience from SPSS, an IBM Company—IBM SPSS Modeler Web Mining sets a new standard for Web analysis. You can easily transform raw Web data into analysis-ready business events using the integrated Web mining source node. These business events are then available within predictive Web analysis applications that quickly deliver actionable insight throughout your organization.

With IBM SPSS Modeler Web Mining, you can enable online business decision makers to take more effective action by giving them the ability to:

• Automatically discover user segments
• Detect the most significant sequences
• Understand product and content affinities
• Predict user propensity to convert, buy, or churn

Quickly deliver predictive insight

The IBM SPSS Modeler Web Mining Application Template combines the power and flexibility of the IBM SPSS Modeler workbench with predictive Web analysis applications designed to quickly deliver online insight. Since business event data is automatically prepared, Web analysis applications are easily executable without previous Web mining experience—eliminating the need for specialist support.

IBM SPSS Modeler Web Mining brings all the benefits of the award-winning IBM SPSS Modeler workbench to predictive Web analysis—including easy data preparation, scalability, and interactive visualization. IBM SPSS Modeler’s visualization techniques accelerate time-to-insight with the ability to derive new attributes and metrics. Unlike traditional Web analytics—which is limited to predefined, generic data—IBM SPSS Modeler Web Mining provides unrivaled flexibility to perform the additional data preparation required for actionable insight. Business event data can even be combined with data from other channels—such as transactional data and textual data from call center notes—for multi-channel analysis.

• Hardware and operating system, Microsoft® Windows®:
  • Windows Vista®, for both 32-and 64-bit processors; or
  • Windows Server™ 2003 (Terminal Services, Standard, or Enterprise), or Windows Server 2003 R2, (Standard or Enterprise) for 32-bit processors; or
  • Windows Server 2003 x64 or Windows Server 2003 R2 x64 (Standard or Enterprise), for 64-bit processors
  • Windows XP Professional with Service Pack 2 for 32-bit processors, or Windows XP Professional x64 Edition for 64-bit processors
  • Intel® Pentium®-compatible processor or faster, with a minimum of 256MB RAM; 512MB RAM strongly recommended
  • CD-ROM drive for installation
• Hardware and operating system, Sun™ Solaris™:
  • Solaris 9 or 10 (for SPARC 64-bit machines) and a minimum of 512MB RAM.
  • CD-ROM drive for installation
• Minimum free drive space: 100MB, after installation. In addition, you will need disk space equal to two times the uncompressed size of the largest log file that you plan to import. (This could equal 1GB or more.) Note: you will need this disk space for processing, even if you plan to store your output in a database.
• Database (optional): Microsoft SQL Server™ or Oracle 10g, configured so that it has ODBC connectivity to the Web Mining host computer. The database needs enough disk space to hold your imported data. (This could equal 1GB or more.)
• Software: Clementine 11.1, 12.0 or IBM SPSS Modeler. In addition, a copy of Microsoft Excel® 2000 (or another application that opens Excel files), in order to use the events and channels definition workbooks.