Deep Learning for Predicting Asset Returns
This addresses the challenge of asset pricing for financial analysts, but it is incremental as it applies existing deep learning methods to a known dataset.
The paper tackled the problem of predicting asset returns by using deep learning to identify nonlinear factors, finding that these factors explain predictability, especially at the extremes of the characteristic space.
Deep learning searches for nonlinear factors for predicting asset returns. Predictability is achieved via multiple layers of composite factors as opposed to additive ones. Viewed in this way, asset pricing studies can be revisited using multi-layer deep learners, such as rectified linear units (ReLU) or long-short-term-memory (LSTM) for time-series effects. State-of-the-art algorithms including stochastic gradient descent (SGD), TensorFlow and dropout design provide imple- mentation and efficient factor exploration. To illustrate our methodology, we revisit the equity market risk premium dataset of Welch and Goyal (2008). We find the existence of nonlinear factors which explain predictability of returns, in particular at the extremes of the characteristic space. Finally, we conclude with directions for future research.