Credit Scoring by Example in SAS® Enterprise Miner™

[#1]

Download the Files (GitHub)

This "learn by example" tip walks you through a classic credit scoring data mining flow. Use this link to download the files you need from SAS Software's github. You can import the XML into SAS Enterprise Miner to recreate a flow diagram. Use the PDF file of each example to read more details on how to build your flow diagram step by step.

In a nutshell, you create the basic Credit Scoring flow for the CS_ACCEPTS data set using these nodes:

• Data Partition node to create a validation set and prevent overfitting
• Interactive Grouping node to bin your input variables, visually inspect the weight of evidence trend, and override with a manual weight of evidence if necessary.
• Scorecard node to train a logistic regression on the weight of evidence of your binned inputs, and to translate the results of your regression into a scorecard that is easy to interpret.

As a bonus, you create a Reverse Scorecard. With one quick property change, you change the order of the scale for your scorecard. Usually the higher the score, the less likely you expect to see an event (payment default). In a reverse scorecard it is the opposite, the higher the score the more likely you expect to see an event.

Another example in the same repository walks you through a flow diagram for Reject Inference. You can use use this diagram to account for sample bias, as long as you have a Rejects data set.

As part of the documentation of the repository for this example, the PDF document briefly describes the fuzzy method for reject inference. Find more information about other methods in the Credit Scoring section of the Reference Help, and a visual explanation of these methods in the video, Reject Inference in SAS Enterprise Miner:

Useful links:

• How to build a scorecard using Credit Scoring for SAS® Enterprise Miner™, is another tip that walks you through some detailed screenshots on how to manually adjust the weight of evidence of your groupings, and how to interpret your scorecard model.
• SAS Enterprise Miner Reference Help: SAS Credit Scoring
• Siddiqi, Naeem, Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring, Cary, NC: SAS Press, 2005.
• Find similar learn by example tips in this directory: Learn by Example using SAS® Enterprise Miner™ and in the Data Mining GitHub repository.

Feel free to post questions or comments!

-Miguel