A Deep Deterministic Policy Gradient-based Strategy for Stocks Portfolio Management

TL;DR

This paper introduces a novel stock portfolio management strategy using Deep Deterministic Policy Gradient reinforcement learning, demonstrating superior returns and risk-adjusted performance compared to existing methods on US stocks.

Contribution

The paper presents a new reinforcement learning-based portfolio strategy with neural networks, outperforming traditional strategies in return and Sharpe Ratio.

Findings

Achieved a 14.12% compound annual return rate.

Outperformed seven other strategies in experiments.

Sharpe Ratio nearly 33% higher than second-best.

Abstract

With the improvement of computer performance and the development of GPU-accelerated technology, trading with machine learning algorithms has attracted the attention of many researchers and practitioners. In this research, we propose a novel portfolio management strategy based on the framework of Deep Deterministic Policy Gradient, a policy-based reinforcement learning framework, and compare its performance to that of other trading strategies. In our framework, two Long Short-Term Memory neural networks and two fully connected neural networks are constructed. We also investigate the performance of our strategy with and without transaction costs. Experimentally, we choose eight US stocks consisting of four low-volatility stocks and four high-volatility stocks. We compare the compound annual return rate of our strategy against seven other strategies, e.g., Uniform Buy and Hold, Exponential Gradient and Universal Portfolios. In our case, the compound annual return rate is 14.12%, outperforming all other strategies. Furthermore, in terms of Sharpe Ratio (0.5988), our strategy is nearly 33% higher than that of the second-best performing strategy.