Skip to main content

         This documentation site is for previous versions. Visit our new documentation site for current releases.      

This content has been archived and is no longer being updated.

Links may not function; however, this content may be relevant to outdated versions of the product.

Predictive Analytics Director (PAD) portal enhancements

Updated on May 1, 2020

The Predictive Analytics Director (PAD) portal features improvements to operations on huge customer databases, the data preparation stage, and the analysis stage. You no longer need to create simulations for scorecards to validate scorecard results against a huge list of customers that are stored in a database. To facilitate the model building process, you can specify special values for predictors, visualize raw distribution of predictors, inspect predictor groups, and set sequencing options.

  • The PAD Scorecard can be generated as an SQL query that you can copy and execute on a customer database. This change facilitates the generation of individual customer scores on huge customer databases. For more information, see Creating a regression model in the Hall of Fame.

    A sample SQL query for a scorecard

    An SQL query generated for a scorecard

  • Special values can be added for numeric predictors. For more information, see Managing binning options for the numeric predictors.

    Details of a numeric predictor

    Details of a numeric predictor

  • A histogram of the raw distribution helps you to better understand predictors. For more information, see Raw distribution.

    A sample histogram

    Histogram that shows the raw distribution of predictors

  • The Data analysis step includes a group view for predictors. For more information, see Analyzing data.

  • The Sequencing option is now visible in the Predictor grouping step. For more information, see Grouping predictors.

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best. is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us