Journal of Korean Society for Quality Management (품질경영학회지)

Korean Society for Quality Management (한국품질경영학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on DRL-based Efficient Asset Allocation Model for Economic Cycle-based Portfolio Optimization

심층강화학습 기반의 경기순환 주기별 효율적 자산 배분 모델 연구

  • 정낙현 (서울과학종합대학원대학교 경영학과) ;
  • 오태연 (서울과학종합대학원대학교 AI첨단학과) ;
  • 김강희 (LG화학 생명과학본부)
  • Received : 2023.10.23
  • Accepted : 2023.11.27
  • 발행 : 2023.12.31
Download PDF
⟨ Previous Next ⟩

초록

Purpose: This study presents a research approach that utilizes deep reinforcement learning to construct optimal portfolios based on the business cycle for stocks and other assets. The objective is to develop effective investment strategies that adapt to the varying returns of assets in accordance with the business cycle. Methods: In this study, a diverse set of time series data, including stocks, is collected and utilized to train a deep reinforcement learning model. The proposed approach optimizes asset allocation based on the business cycle, particularly by gathering data for different states such as prosperity, recession, depression, and recovery and constructing portfolios optimized for each phase. Results: Experimental results confirm the effectiveness of the proposed deep reinforcement learning-based approach in constructing optimal portfolios tailored to the business cycle. The utility of optimizing portfolio investment strategies for each phase of the business cycle is demonstrated. Conclusion: This paper contributes to the construction of optimal portfolios based on the business cycle using a deep reinforcement learning approach, providing investors with effective investment strategies that simultaneously seek stability and profitability. As a result, investors can adopt stable and profitable investment strategies that adapt to business cycle volatility.

키워드

참고문헌

  1. Chi, H. 1998. Circulative Relation of Stock, Bond, Real Estate Markers to Business Cycle. Korean Management Review 27(5):1277-1296.
  2. Durall, R. 2022. Asset Allocation: From Markowitz to Deep Reinforcement Learning. arXiv preprint arXiv:2208.07158.
  3. Fujimoto, S., Hoof, H., and Meger, D. 2018. Addressing function approximation error in actor-critic methods. In International conference on machine learning (pp. 1587-1596). PMLR.
  4. Gu, S., and Jang, S. 2010. A Study on the Strategy for Optimizing Investment Portfolios. Industrial Engineers Interfaces 23(4):300-310.
  5. Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning (pp. 1861-1870). PMLR.
  6. JUNG, N. H., Oh, T., and Kim, K. H. 2023. A Study on AI-based Composite Supplementary Index for Complementing the Composite Index of Business Indicators. Journal of Korean Society for Quality Management 51(3):363-379.
  7. Kang, H., Bae, K., Yang, S., and Choi, C. 2019. An Investment Strategy Based on Life and Business Cycles. Korean Journal of Financial Studies 48(6):721-754.
  8. Kim, H., and Kim, H. T. 2015. Finding optimal portfolio based on genetic algorithm with generalized Pareto distribution. Journal of the Korean Data and Information Science Society. Korean Data and Information Science Society 26(6):1479-1494.
  9. Kim, J. 2015. Study on Interrelation between the Composite Leading Index, Coincident Composite Index and Lagging Composite Index. Journal of CEO and Management Studies 18(4):105-122.
  10. Kim, T., and Ko, B. 2021. Modular reinforcement learning for dynamic portfolio optimization in the KOSPI market. Journal of the Korean Data And Information Science Society. Korean Data and Information Science Society 32(1):213-226.
  11. KIM, Y., Kim, D., and Kang, K. H. 2016. Bayesian Analysis of Optimal Foreign Currency Portfolio Selection. Financial Stability Studies 17(1):121-162.
  12. Ko, B. 2021. A Study on the Reorganization of Economic Composite Index in Jeju. The Journal of Humanities and Social Science 12(5):1215-1230.
  13. Koo, G. d., and Lee, J. G. 2013. A Study on the Portfolio Construction by Optimal Simulation. Korea Management Engineers Society 18(2):133-144
  14. Lee, Y. B., and Baek, J. S. 2016. The Interconnectedness between Foreign Exchange Rate on Stock Price and Macroeconomic Variables in Korea and the U.S. Korean Journal of Business Administration 29(10):1459-1480.
  15. Li, T., and Kim, C. S. 2013. Correlation of Business Cycle and Asset Allocation. Korean Association for Accounting and Policy, 18(2):303-315.
  16. Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., ... and Wierstra, D. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971.
  17. Lim, Q. Y. E., Cao, Q., and Quek, C. 2022. Dynamic portfolio rebalancing through reinforcement learning. Neural Computing and Applications 34(9):7125-7139.
  18. Markowitz, H., 1952, Portfolio Selection, Journal of Finance 7(1):77-91.
  19. Metropolis, N., and Ulam, S. 1949. The monte carlo method. Journal of the American statistical association,44(247):335-341.
  20. Mnih, V., Badia, C. A. P., Mirza, C. M., and CA, U. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning (pp. 1928-1937). PMLR.
  21. Park, K., and Shin, H. 2013. Stock Trading Model using Portfolio Optimization and Forecasting Stock Price Movement. Journal of Korean Institute of Industrial Engineers. Korean Institute of Industrial Engineers 39(6):535-545.
  22. Park, S., and Cho, Y. 2015. A Study on Efficient Frontier and Optimal Portfolio under Emissions Trading Scheme. International Area Studies Review 19(1):383-413.
  23. Park, S., Lee, H., Rhee, Y., and Jang, B. 2014. Portfolio Management with the Business Cycle and Bayesian Learning. Journal of The Korean Operations Research and Management Science Society 39(2):49-66.
  24. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.
  25. Schumpeter, J. A. 1939. Business cycles (Vol. 1, pp. 161-174). New York: Mcgraw-hill.
  26. Sharpe, W. F. 1998. The sharpe ratio. Streetwise-the Best of the Journal of Portfolio Management 3:169-85.
  27. Song, J.H.,Choi, H. S., and Kim, S. W. 2017. A Study on Commodity Asset Investment Model Based on Machine Learning Technique. Journal of Intelligence and Information Systems 23(4):127-146.
  28. Sood, S., Papasotiriou, K., Vaiciulis, M., and Balch, T. 2023. Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization. FinPlan 2023, 21.
  29. Sortino, F. A., and Van Der Meer, R. 1991. Downside risk. Journal of Portfolio Management 17(4):27.
  30. Woo, D. H., Choi, H. S., and Kim, S. W. 2023. Magic Formula Investment Strategy Performance Analysis in the Korean Stock Market. Journal of the Korea Academia-Industrial Cooperation Society 24(3):508-519.
  31. Yang, H., and Kang, C. 2015. Analysis of the Optimal Mixed Asset Portfolio and Implication before and after the Global Financial Crisis -An Empirical Analysis of K-REITs-. Korea Real Estate Society 33(2):307-325.