Model Risk Under CECL: A Consumer Finance Perspective

Supersedes Working Paper 24-03 – CECL Implementation and Model Risk in Uncertain Times: An Application to Consumer Finance

He documents the increased sensitivity to model and macroeconomic forecasting error of the CECL framework with respect to the incurred loss framework that it replaces. An empirical application illustrates how to leverage simple machine learning (ML) strategies and statistical principles in the design of a nimble and flexible CECL modeling framework. The author shows that, even in consumer loan portfolios with tens of millions of loans, like mortgage, auto, or credit card portfolios, one can develop, estimate, and deploy an array of models quickly and efficiently, and without a forecasting performance penalty. Drawing on more than 20 years of auto loans data and the experience from the Great Recession and the COVID-19 pandemic, he leverages basic econometric principles to identify strategies to deal with biased model projections in times of high economic uncertainty. He advocates for a focus on resiliency and adaptability of models and model infrastructures to novel shocks and uncertain economic conditions.