Deep Factor Alpha
share
Deep Factor Alpha provides a framework for extracting nonlinear factors information to explain the time-series cross-section properties of asset returns. Sorting securities based on firm characteristics is viewed as a nonlinear activation function which can be implemented within a deep learning architecture. Multi-layer deep learners are constructed to augment traditional long-short factor models. Searching firm characteristic space over deep architectures of nonlinear transformations is compatible with the economic goal of eliminating mispricing Alphas. Joint estimation of factors and betas is achieved with stochastic gradient descent. To illustrate our methodology, we design long-short latent factors in a train-validation-testing framework of US stock market asset returns from 1975 to 2017. We perform an out-of-sample study to analyze Fama-French factors, in both the cross-section and time-series, versus their deep learning counterparts. Finally, we conclude with directions for future research.
READ FULL TEXT