Factor Representation and Decision Making in Stock Markets Using Deep Reinforcement Learning

TL;DR

This paper develops a deep reinforcement learning-based portfolio management system that learns factor representations to make optimal stock investment decisions, significantly outperforming the market average.

Contribution

It introduces a novel approach using deep reinforcement learning to directly learn factor representations for portfolio optimization in stock markets.

Findings

The system effectively models market conditions and makes superior portfolio choices.

It significantly outperforms the average market in experimental results.

Abstract

Deep Reinforcement learning is a branch of unsupervised learning in which an agent learns to act based on environment state in order to maximize its total reward. Deep reinforcement learning provides good opportunity to model the complexity of portfolio choice in high-dimensional and data-driven environment by leveraging the powerful representation of deep neural networks. In this paper, we build a portfolio management system using direct deep reinforcement learning to make optimal portfolio choice periodically among S\&P500 underlying stocks by learning a good factor representation (as input). The result shows that an effective learning of market conditions and optimal portfolio allocations can significantly outperform the average market.