Taking the perspective of international asset allocation, this paper tests if predictive regressions conditional on time-series and cross-sectional information can improve forecasts of stock index returns. We use different current price-to-fundamental ratios as predictors and condition the...

This paper employs a deep learning approach for linking stock market fundamentals to trading signals via neural networks. With an average accuracy of ~54% the model predicts whether markets go up or down on the subsequent trading day. Coupling the prediction to a binary long/cash strategy yields...