Fair Isaac Corporation, a leading provider of analytics and decision technology, announced release 2.1 of Model Builder for Predictive Analytics, an advanced modeling platform specifically designed to jump-start the predictive modeling process, enabling rapid development and deployment of predictive models into enterprise-class decision applications. The new release lets clients create more accurate predictive scores with performance inference processing and integrate Model Builder more easily into mainframe environments.

Model Builder's advanced modeling capabilities support the design and deployment of decision management applications that can be configured to meet the unique needs of different businesses. Clients can quickly define, test, and deploy models to production systems including mainframes without recoding by programmers. This lets companies move from data analysis to production status much faster than has been possible with traditional modeling software with fewer modeling errors, better compliance with regulatory requirements, and easier monitoring and modification of decision models.

In an analysis of Model Builder for Predictive Analytics performed by Elder Research, Inc., distinguished research scientists John F. Elder, Ph.D., and J. Dustin Hux found that "Model Builder is a clear contender for top-of-the-line data mining and analysis tool. It is likely unparalleled in scorecard technology - Fair Isaac's strength - and is competitive in a growing suite of analysis capabilities. Importantly, Model Builder for Predictive Analytics streamlines the integration process, from analysis to production, enabling massive scalability on legacy systems."

Model Builder for Predictive Analytics in release 2.1 offers companies several improvements in functionality and implementation:

  • Performance inference processing in scorecard modeling allows users to infer the performance of data observations previously eliminated from studied populations due to selection methods or other subjective sample biases. This methodology results in better quality scorecard models achieved by exploiting the most predictive value possible from available data sources.
  •  Model Builder can use mainframe data files in their native binary format from systems such as IBM OS/390 to perform modeling without requiring intermediate data transformations. This lets companies more easily access and analyze the data from their largest production systems.
  •  Efficiency improvements include faster data processing and enhancements to the graphical user interface (GUI) for modelers.

Other functionality enhancements span the entire modeling life cycle. These include improvements in accessing and managing data, additional statistics for data analysis, new modeling options, improved performance reporting and the addition of reason codes to explain scorecard model outputs. There are also enhancements to allow easier and more extensive user customizations.
The combination of data analytics, modeling, and policy-level control in Fair Isaac's enterprise decision management software lets companies define and manage their automated business systems for improved efficiency and greater profitability. Fair Isaac offers clients project management, implementation assistance, data analysis, and model preparation in support of their use of Model Builder. Fair Isaac software and services allow an enterprise to quickly implement customized systems that lower operational costs, reduce risk, and provide greater accuracy and consistency of critical business decisions in interactive and batch applications.

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access