Deep Reinforcement Learning Agent for S&P 500 Stock Selection

This study investigated the performance of a trading agent based on a convolutional neural network model in portfolio management. The results showed that with real-world data the agent could produce relevant trading results, while the agent’s behavior corresponded to that of a high-risk taker. The data used were wide in comparison with earlier reported research and was based on the full set of the S&P 500 stock data for twenty-one years supplemented with selected financial ratios. The results presented are new in terms of the size of the data set used and with regards to the model used. The results provide direction and offer insight into how deep learning methods may be used in constructing automatic trading systems.

[1]  Saejoon Kim,et al.  Index tracking through deep latent representation learning , 2020 .

[2]  Chi-Guhn Lee,et al.  Continuous control with Stacked Deep Dynamic Recurrent Reinforcement Learning for portfolio optimization , 2020, Expert Syst. Appl..

[3]  R. Banz,et al.  The relationship between return and market value of common stocks , 1981 .

[4]  Yong Wang,et al.  Stock Market Prediction Based on Generative Adversarial Network , 2018, IIKI.

[5]  Maureen O'Hara,et al.  Market Statistics and Technical Analysis: The Role of Volume , 1994 .

[6]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[7]  Brian J. Bushee,et al.  Abnormal Returns to a Fundamental Analysis Strategy , 1997 .

[8]  E. Fama,et al.  Dividend yields and expected stock returns , 1988 .

[9]  Chih-Fong Tsai,et al.  Using neural network ensembles for bankruptcy prediction and credit scoring , 2008, Expert Syst. Appl..

[10]  Ying Wang,et al.  Fuzzy Adaptive DSC Design for an Extended Class of MIMO Pure-Feedback Non-Affine Nonlinear Systems in the Presence of Input Constraints , 2019, Mathematical Problems in Engineering.

[11]  Nicolas Huck,et al.  Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500 , 2017, Eur. J. Oper. Res..

[12]  Sheridan Titman,et al.  Mutual Fund Performance: An Analysis of Quarterly Portfolio Holdings , 1989 .

[13]  Steve Y. Yang,et al.  An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown , 2017, Expert Syst. Appl..

[14]  Matthew Saffell,et al.  Learning to trade via direct reinforcement , 2001, IEEE Trans. Neural Networks.

[15]  Ah Chung Tsoi,et al.  Noisy Time Series Prediction using Recurrent Neural Networks and Grammatical Inference , 2001, Machine Learning.

[16]  S. Basu.  The relationship between earnings' yield, market value and return for NYSE common stocks: Further evidence , 1983 .

[17]  Narasimhan Jegadeesh,et al.  Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency , 1993 .

[18]  Jinho Lee,et al.  Effectively training neural networks for stock index prediction: Predicting the S&P 500 index without using its index data , 2020, PloS one.

[19]  Jonghun Park,et al.  A Multiagent Approach to $Q$-Learning for Daily Stock Trading , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[20]  J. Moody,et al.  Performance functions and reinforcement learning for trading systems and portfolios , 1998 .

[21]  R. Bellman.  The theory of dynamic programming , 1954 .