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...

This paper analyzes empirically the relation between financial analysts' recommendation profitability and their forecast accuracy and shows that contrary to intuition the group of most successful recommendations is not associated with the highest accuracy on average. The finding that best...