factual

Machine Learning Beat Expert Systems In Underwriting

In Kling's experience at Freddie Mac in the early 1990s, the statistical, correlation-based credit-scoring approach (an early form of machine learning) beat rule-based expert systems at automating underwriting, because it discovered predictive variables human underwriters ignored—such as unused credit capacity signaling low default risk and many recent credit inquiries signaling high risk.

factualpending

Speaker

Arnold Kling

Evidence Quote

“The statistical-based or machine-learning type... won out and the expert systems lost.”

Source

Arnold Kling on Twitter, FTX, and ChatGPT— EconTalk
Created: 6/13/2026, 12:21:58 AM

Your notes

Loading notes...