We design a novel framework to examine market efficiency through out-of-sample (OOS) predictability. We frame the asset pricing problem as a machine learning classification problem and construct classification models to predict return states. The prediction-based portfolios beat the market with significant OOS economic gains. We measure prediction accuracies directly. For each model, we introduce a novel application of binomial test to test the accuracy of 3.34 million return state predictions. The tests show that our models can extract useful contents from historical information to predict future return states. We provide unique economic insights about OOS predictability and machine learning models.
Download