Stock Price Predictability and the Business Cycle via Machine Learning
This highlights a limitation for financial practitioners using ML in stock price prediction, showing that performance is context-dependent and incremental in understanding model robustness.
The study examined how business cycles affect machine learning predictions for the S&P 500 index, finding that models perform worse during most recessions and that improved performance in some recessions is linked to lower market volatility rather than ML methods.
We study the impacts of business cycles on machine learning (ML) predictions. Using the S&P 500 index, we find that ML models perform worse during most recessions, and the inclusion of recession history or the risk-free rate does not necessarily improve their performance. Investigating recessions where models perform well, we find that they exhibit lower market volatility than other recessions. This implies that the improved performance is not due to the merit of ML methods but rather factors such as effective monetary policies that stabilized the market. We recommend that ML practitioners evaluate their models during both recessions and expansions.