English

Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution

Artificial Intelligence 2021-02-09 v2 Machine Learning

Abstract

Portfolio management via reinforcement learning is at the forefront of fintech research, which explores how to optimally reallocate a fund into different financial assets over the long term by trial-and-error. Existing methods are impractical since they usually assume each reallocation can be finished immediately and thus ignoring the price slippage as part of the trading cost. To address these issues, we propose a hierarchical reinforced stock trading system for portfolio management (HRPM). Concretely, we decompose the trading process into a hierarchy of portfolio management over trade execution and train the corresponding policies. The high-level policy gives portfolio weights at a lower frequency to maximize the long term profit and invokes the low-level policy to sell or buy the corresponding shares within a short time window at a higher frequency to minimize the trading cost. We train two levels of policies via pre-training scheme and iterative training scheme for data efficiency. Extensive experimental results in the U.S. market and the China market demonstrate that HRPM achieves significant improvement against many state-of-the-art approaches.

Keywords

Cite

@article{arxiv.2012.12620,
  title  = {Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution},
  author = {Rundong Wang and Hongxin Wei and Bo An and Zhouyan Feng and Jun Yao},
  journal= {arXiv preprint arXiv:2012.12620},
  year   = {2021}
}

Comments

This paper was accepted by AAAI 2021 with the original title: Commission Fee is not Enough: A Hierarchical Reinforced Framework for Portfolio Management

R2 v1 2026-06-23T21:16:59.170Z