Browse > Article
http://dx.doi.org/10.21289/KSIC.2022.25.4.645

A Study on Asset Allocation Using Proximal Policy Optimization  

Lee, Woo Sik (College of Business Administration, Gyeongsang National University)
Publication Information
Journal of the Korean Society of Industry Convergence / v.25, no.4_2, 2022 , pp. 645-653 More about this Journal
Abstract
Recently, deep reinforcement learning has been applied to a variety of industries, such as games, robotics, autonomous vehicles, and data cooling systems. An algorithm called reinforcement learning allows for automated asset allocation without the requirement for ongoing monitoring. It is free to choose its own policies. The purpose of this paper is to carry out an empirical analysis of the performance of asset allocation strategies. Among the strategies considered were the conventional Mean- Variance Optimization (MVO) and the Proximal Policy Optimization (PPO). According to the findings, the PPO outperformed both its benchmark index and the MVO. This paper demonstrates how dynamic asset allocation can benefit from the development of a reinforcement learning algorithm.
Keywords
Quantitative Finance; Business Analytics; FinTech; Robo-Advisor; Reinforcement Learning;
Citations & Related Records
Times Cited By KSCI : 5  (Citation Analysis)
연도 인용수 순위
1 B. Michael, and R. Grauer, "On the Sensitivity of Mean-Variance-Efficient Portfolios to Changes in Asset Means: Some Analytical and Computational Results," Review of Financial Studies, vol. 4, pp.315-342, (1991).   DOI
2 I. Choi, and K. Ha, "A Study on a Method for Portfolio Construction using Dynamic Multi-Factor Model and Black-Litterman-Herold Model," Journal of The Korean Data Analysis Society, vol. 13, no. 5, pp.2599-2613, (2011).
3 Graesser, L. and Keng, W. L. : Foundations of Deep Reinforcement Learning: Theory and Practice in Python.1st Ed., Addison-Wesley Professional. Press, Boston, (2019).
4 A. Harman, v. d. L. Epco, S. Kej, and K. Petr, "Dynamic Asset Allocation," Colonial First State Global Asset Management Multi-Asset Solutions Research Papers, no. 7, New York, (2017).
5 W. J. Fan, Y. Liao, and M. Mincheva, "Large Covariance Estimation by Thresholding Principal Orthogonal Complements," Journal of the Royal Statistical Society. Series B (Statistical Methodology), vol. 75, no. 4, pp.603-680, (2013).   DOI
6 T. T. Cai, W. Liu, and X. Luo, "A Constrained L1 Minimization Approach to Sparse Precision Matrix Estimation," Journal of the American Statistical Association, vol. 106, pp.591-607, (2011).
7 T. Millington, and M. Niranjan, "Robust Portfolio Risk Minimization Using the Graphical Lasso," International Conference on Neural Information Processing, pp.863-872, (2019).
8 S. Yoon, and S. Lee, "Stock Portfolio Construction and Trading Simulation Using Reinforcement Learning," Management & Information Systems Review, vol. 40, no. 4, pp.185-203, (2021).   DOI
9 K. Cho, S. Lee, and J. Kim, "An Empirical Study on the Risk Diversification Effect of REITs," Korean Journal of Construction Engineering and Management, vol. 14, no. 1, pp.23-31, (2013).   DOI
10 J. Kim, J. Heo, H. Lim, D. Kwon, and Y. Han, "Blockchain Based Financial Portfolio Management Using A3C," KIPS Transactions on Computer and Communication Systems, vol. 8, no. 1, pp.17-28, (2019).   DOI
11 W. Lee, "Performance Evaluation of Portfolio using a Deep Q-Networks," Journal of Next-generation Convergence Information Services Technology, vol. 10, no. 4, pp.459-470, (2021).   DOI
12 D. Lee, and M. Kwon, "Combating Stop-and-Go Wave Problem at a Ring Road Using Deep Reinforcement Learning Based Autonomous Vehicles," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 10, pp.1667-1682, (2021).   DOI
13 Hankyung Magazine, "https://magazine.hankyung.com/business/article/202201058897b"
14 W. S. Lee, "A Study on Portf olio based on a Deep Deterministic Policy Gradient," Journal of Next-generation Convergence Information Services Technology, vol. 11, no. 3, pp.287-298, (2022).   DOI
15 W. S. Lee, "A Study on the Portf olio Performance Evaluation using Actor-Critic Reinforcement Learning Algorithms," Journal of The Korean Society of Industry Convergence, vol. 25, no. 3, pp.467-476, (2022).   DOI
16 E. Pantaleo, M. Tumminello, F. Lillo, and R. Mantegna, "When do improved covariance matrix estimators enhance portfolio optimization? An empirical comparative study of nine estimators," Quantitative Finance, vol. 11, pp. 1067-1080, (2011).   DOI
17 W. Yoo, and Y. Choi, "A Study on the Improvement of Strategic Asset Allocation Using Global Investor's Reference Portfolio," Korea Finance Association Conference, pp. 214-324, (2019).
18 M. h. Choi, and J. Sung, "Why should Government Alleviate the Current Regulation of Defined Contribution Pension Asset Management in Korea?," Journal of The Korean Data Analysis Society, vol. 13, no. 5, pp.2629-2642, (2011).
19 J. Bouchaud, M Potters, and J. Aguilar, "Missing Information and Asset Allocation," Science & Finance (CFM) working paper archive 500045, Science & Finance, Capital Fund Management, (1997).
20 I. Song, "Using Decision Making Model for Asset Allocation," Asset Management Review, vol. 7, no. 2, pp.46-64, (2019).   DOI
21 H. Chae, D. Lee, S. Park, H. Choi and H. Park, "Time-varying Proportional Navigation Guidance using Deep Reinforcement Learning," Journal of the Korea Institute of Military Science and Technology, vol. 23, no. 4, pp. 399-406, (2020).   DOI
22 J. Lee, Y. Lee, and Y. Cho, "Perf ormance analysis of sector index portfolios using the GOP model," Journal of the Korean Data Analysis Society, vol. 24, no. 2, pp.823-841, (2022).   DOI
23 J. Hahn, S. Park, and H. E. Young, "Evaluating the Empirical Performance of Risk-based Portfolio Strategies in the Korean Stock Market," The Korean Journal of applied Statistics, vol. 45, no. 2, pp.247-284, (2016).
24 Koscom Newsroom, "https://newsroom.koscom.co.kr/27881"
25 Y. Kim, H. Kim, and S. Kim, "Application of Tracking Signal to the Markowitz Portfolio Selection Model to Improve Stock Selection Ability by Overcoming Estimation Error," Journal of the Korean Operations Research and Management Science Society, vol. 41, no. 3, pp.1-21, (2016).   DOI
26 D. Ahn, and S. Park, "Linear programming models using a Dantzig type risk f or portf olio optimization," The Korean Journal of applied Statistics, vol. 35, no. 2, pp.229-250, (2022).   DOI