Research Area:  Machine Learning
In this article, the authors adopt deep learning models to directly optimize the portfolio Sharpe ratio. The framework they present circumvents the requirements for forecasting expected returns and allows them to directly optimize portfolio weights by updating model parameters. Instead of selecting individual assets, they trade exchange-traded funds of market indexes to form a portfolio. Indexes of different asset classes show robust correlations, and trading them substantially reduces the spectrum of available assets from which to choose. The authors compare their method with a wide range of algorithms, with results showing that the model obtains the best performance over the testing period of 2011 to the end of April 2020, including the financial instabilities of the first quarter of 2020. A sensitivity analysis is included to clarify the relevance of input features, and the authors further study the performance of their approach under different cost rates and different risk levels via volatility scaling.
Keywords:  
Reinforcement learning
Stochastic control
Portfolio optimization
Author(s) Name:  Ayman Chaouki, Stephen Hardiman, Christian Schmidt, Emmanuel Sérié, Joachim de Lataillade
Journal name:  The Journal of Finance and Data Science
Conferrence name:  
Publisher name:  Elsevier
DOI:  10.1016/j.jfds.2020.06.002
Volume Information:  Volume 6, November 2020, Pages 16-30
Paper Link:   https://www.sciencedirect.com/science/article/pii/S2405918820300118