Overhyped? Can ML Models Reliably Predict Stock Returns?
By Yanki Kalfa in Working-Paper
Hyperparameters determine the architecture of machine learning (ML) models and
can greatly affect their forecasting performance, yet there is little consensus on how to
choose the range and grid of hyperparameters to search over. We provide an extensive
examination of which hyperparameters are most important for popular ML models’
out-of-sample forecasting performance using a large U.S. dataset on individual stock
returns and firm characteristics. We find that some choices of hyperparameters virtu-
ally guarantee good out-of-sample return forecasts while others lock in poor forecasts.
This poses a challenge because many empirical studies fail to provide details on how
they set their hyperparameters. We also find that time-series validation methods do
not offer a definitive solution to the dependence of out-of-sample return forecasting
performance on the underlying range of hyperparameters.