Machine Learning and Shrinkage in Dynamic Panel Forecasting

Abstract

This paper studies forecasting in dynamic panel data models with fixed effects. We compare the forecasting accuracy of conventional estimators—pooledOLS,fixed effects, Anderson–Hsiao, and Arellano–Bond—against shrinkage and regularization methods such as Ridge, LASSO, ElasticNet, empirical Bayes maximum likelihood and the recent unbiased risk estimation of Kwon (2026). Monte Carlo evidence shows that shrinkage methods substantially improve out-of-sample accuracy. An empirical application to firm-level leverage dynamics using Compustat data confirms the relevance of these findings for forecasting in corporate finance. Machine learning regularization can improve forecasting performance in dynamic panel settings while preserving the structural framework.