Daily Market Return Prediction with Transformer
Date:
Conference presentation at 15th International Conference of the Financial Engineering and Banking Society (FEBS),
Presentation of the working paper Daily Market Return Prediction with Transformer.
We apply a Transformer encoder to forecast daily market returns using lagged market returns over horizons of 5, 20, and 60 days. Both the direct model forecasts and post-machine learning forecasts exhibit significant predictive power for next-day returns, while simple averages of past returns do not. Relative to linear predictive regressions, the machine learning forecasts deliver sizable improvements in out-of-sample R-squared.
Co-authors: Yufeng Han (UNC Charlotte), Guofu Zhou (Washington University in St. Louis)