Picking the Y variable, picking the X variables
Abstract
This chapter provides examples of how credit data is turning into variables that together predict very generally whether people will pay back the loans they take on. The most useful variable is one that shows how much money the borrower can still get from revolving credit cards. This variable shows the degree credit card companies have come to trust a person, growing larger as the consumer ages or if his or her wealth or income is higher. However, this is a data-mining exercise, not a meaning exercise. Other variables of importance are recency of delinquency, depth of delinquency, and number of recent tries for debt. I show some common graphical techniques and how ...
Get Credit Data and Scoring now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
