Deep Learning for Portfolio Optimization

TL;DR

This paper introduces a deep learning framework that directly optimizes portfolio Sharpe ratio by trading ETFs, outperforming traditional methods and robustly handling market volatility and financial crises.

Contribution

It presents a novel deep learning approach that bypasses return forecasting to directly optimize portfolio weights, demonstrating superior performance over multiple algorithms.

Findings

Outperforms existing algorithms in Sharpe ratio during 2011-2020

Robust performance during the 2020 financial crisis

Effective under various cost and risk scenarios

Abstract

We adopt deep learning models to directly optimise the portfolio Sharpe ratio. The framework we present circumvents the requirements for forecasting expected returns and allows us to directly optimise portfolio weights by updating model parameters. Instead of selecting individual assets, we trade Exchange-Traded Funds (ETFs) of market indices to form a portfolio. Indices of different asset classes show robust correlations and trading them substantially reduces the spectrum of available assets to choose from. We compare our method with a wide range of algorithms with results showing that our model obtains the best performance over the testing period, from 2011 to the end of April 2020, including the financial instabilities of the first quarter of 2020. A sensitivity analysis is included to understand the relevance of input features and we further study the performance of our approach under different cost rates and different risk levels via volatility scaling.