Improving Earnings Predictions and Abnormal Returns with Machine Learning

Abstract

Using use stepwise logit regression, Ou and Penman (1989) predicts the sign of future earnings changes and uses these predictions to form a profitable hedge portfolio. Dramatic increases in computing power and recent advances in machine learning allow us to extend Ou and Penman (1989) using a larger dataset, more computer intensive forecasting algorithms, and modern prediction models. We find that stepwise logit continues to provide good out-of-sample predictions and can be used to form a trading strategy that generates small abnormal returns, but a nonparametric machine learning technique (random forest) significantly improves out-of-sample forecast accuracy and trading strategy returns. We also find that that the models identify different independent variables as being important for prediction in the High Tech and Manufacturing industries, but this does not lead to better predictions or higher trading strategy returns. Overall, the most profitable strategy is based on earnings predictions from a random forest model using our full sample. Our results confirm the Ou and Penman (1989) finding that financial statement information can be useful for investment decisions, and suggest that recent nonparametric machine learning techniques could be useful in a variety of accounting contexts where predictions of binary outcomes are needed.