Footnote:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments January 5, 2022 erstellt
Description:
We examine how the return predictability of deep learning models varies with stocks’ vulnerability to investors’ behavioral biases. Using an extensive list of anomaly variables, we find that the long-short strategy based on deep learning signals generates greater returns for stocks that are more vulnerable to behavioral biases, that is, stocks that are small, unprofitable, volatile, non-dividend-paying, far from the 52-week high, and lottery-like. This performance of deep learning models becomes more pronounced for stocks held by less sophisticated investors. These results suggest that deep learning models with nonlinear structures are useful for capturing mispricing induced by behavioral biases