SavedAdd your journal

Journals / Ekonomi Politika ve Finans Araştırmaları Dergisi / 2026 / Cilt: 11 Sayı: 1

Dynamic Portfolio Optimization with Deep Reinforcement Learning: Evidence from Borsa Istanbul

Derin Pekiştirmeli Öğrenme ile Dinamik Portföy Optimizasyonu: Borsa İstanbul Örneği

Hidayet Beyhan(Bitlis Eren University)0000-0002-0219-7076
Erhan Ergin(BITLIS EREN UNIVERSITY)0000-0001-6281-3654
Binali Selman Eren(BITLIS EREN UNIVERSITY)0000-0001-5136-6406
Pages
106–119
Publication Date
2026-03-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings, while highlighting the potential of RL approaches in practice, emerge as an alternative option for fund managers, especially in a volatile market environment.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, portfolio optimization has been conducted using the reinforcement learning approach, one of the artificial intelligence algorithms.
📊
Key Findings & Data:The data is considered for constituents of the BIST30 index, which is the blue-chip index of Borsa Istanbul.
💡
Conclusion & Impact:These findings, while highlighting the potential of RL approaches in practice, emerge as an alternative option for fund managers, especially in a volatile market environment.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Pekiştirmeli Öğrenme · Portföy Optimizasyonu · Borsa İstanbul

Abstract

In this study, portfolio optimization has been conducted using the reinforcement learning approach, one of the artificial intelligence algorithms. The data is considered for constituents of the BIST30 index, which is the blue-chip index of Borsa Istanbul. The performance of Deep Deterministic Policy Gradient (DDPG), a deep learning algorithm of reinforcement learning, has been tested against the Markowitz mean-variance and equal-weighted portfolios as benchmark models; the BIST30 index itself has also been taken as a benchmark portfolio. This study contributes to the relevant literature in terms of Türkiye as an example of a developing country and the method employed. The study demonstrates the potential of RL approaches that are becoming widespread for portfolio optimization. The obtained results reveal that the portfolio formed with the DDPG approach shows a superior Sharpe ratio portfolio over portfolios obtained with other classical approaches. These findings, while highlighting the potential of RL approaches in practice, emerge as an alternative option for fund managers, especially in a volatile market environment.

Özet

Bu çalışmada, yapay zekâ algoritmalarından biri olan pekiştirmeli öğrenme yaklaşımı kullanılarak portföy optimizasyonu gerçekleştirilmiştir. Veriler, Borsa İstanbul endeksi olan BIST30 endeksinin bileşenleri için ele alınmıştır. Pekiştirmeli öğrenmenin derin öğrenme algoritmalarından biri olan Derin Deterministik Politika Gradyanının (DDPG) performansı, kıyaslama modeli olarak Markowitz ortalama-varyans ve eşit ağırlıklı portföylere karşı test edilmiş, ayrıca BIST30 endeksinin kendisi de kıyaslama portföyü olarak alınmıştır. Bu çalışma, gelişmekte olan bir ülke örneği olarak Türkiye ve kullanılan yöntem açısından ilgili literatüre katkıda bulunmaktadır. Çalışma, giderek yaygınlaşan RL yaklaşımlarının portföy optimizasyonu için potansiyelini göstermektedir. Elde edilen sonuçlar, DDPG yaklaşımıyla oluşturulan portföyün, diğer klasik yaklaşımlarla elde edilen portföylere göre daha üstün bir Sharpe oranına sahip portföy gösterdiğini ortaya koymaktadır. Bu bulgular, RL yaklaşımlarının pratikteki potansiyelini vurgularken, özellikle dalgalı piyasa ortamında fon yöneticileri için alternatif bir seçenek olarak ortaya çıkmaktadır.

🔖

Cite This Article

Beyhan, H., Ergin, E., Eren, B. S. (2026). Dynamic Portfolio Optimization with Deep Reinforcement Learning: Evidence from Borsa Istanbul. Ekonomi Politika ve Finans Araştırmaları Dergisi, Cilt: 11 Sayı: 1, 106–119. https://doi.org/10.30784/epfad.1811319

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (37)

  1. Aboussalah, A.M. and Lee, C.G. (2020). Continuous control with stacked deep dynamic recurrent reinforcement learning for portfolio optimization. Expert Systems with Applications, 140, 112891. https://doi.org/10.1016/j.eswa.2019.112891
  2. Almahdi, S. and Yang, S.Y. (2017). An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Systems with Applications, 87, 267–279. https://doi.org/10.1016/j.eswa.2017.06.023
  3. Bai, Y., Gao, Y., Wan, R., Zhang, S. and Song, R. (2025). A review of reinforcement learning in financial applications. Annual Review of Statistics and Its Application, 12(1), 209–232. https://doi.org/10.48550/arXiv.2411.12746
  4. Bekaert, G. and Harvey, C.R. (2003). Emerging markets finance. Journal of Empirical Finance, 10(1–2), 3–55. https://doi.org/10.1016/S0927-5398(02)00054-3
  5. Black, F. and Litterman, R. (1990). Asset allocation: Combining investor views with market equilibrium. Journal of Fixed Income, 1(2), 7–18. https://doi.org/10.3905/jfi.1991.408013
  6. Black, F. and Litterman, R. (1992). Global portfolio optimization. Financial Analysts Journal, 48(5), 28–43. https://doi.org/10.2469/faj.v48.n5.28
  7. Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J. and Zaremba, W. (2016). OpenAI gym. arXiv preprint arXiv:1606.01540. https://doi.org/10.48550/arXiv.1606.01540
  8. De Prado, M.L. (2016). Building diversified portfolios that outperform out-of-sample. Journal of Portfolio Management, 42(4), 59–69. https://doi.org/10.3905/jpm.2016.42.4.059
  9. Deng, Y., Bao, F., Kong, Y., Ren, Z. and Dai, Q. (2016). Deep direct reinforcement learning for financial signal representation and trading. IEEE Transactions on Neural Networks and Learning Systems, 28(3), 653–664. https://doi.org/10.1109/TNNLS.2016.2522401
  10. Erdoğan, L., Ceylan, R. and Abdul-Rahman, M. (2022). The impact of domestic and global risk factors on Turkish stock market: Evidence from the NARDL approach. Emerging Markets Finance and Trade, 58(7), 1961–1974. https://doi.org/10.1080/1540496X.2021.1949282
  11. Fabozzi, F.J., Kolm, P.N., Pachamanova, D.A. and Focardi, S.M. (2007). Robust portfolio optimization. Journal of Portfolio Management, 33(3), 40–48. https://doi.org/10.3905/jpm.2007.684751
  12. Gort, B.J.D., Liu, X.Y., Sun, X., Gao, J., Chen, S. and Wang, C.D. (2022). Deep reinforcement learning for cryptocurrency trading: Practical approach to address backtest overfitting. arXiv preprint arXiv:2209.05559. https://doi.org/10.48550/arXiv.2209.05559
  13. Jang, J. and Seong, N. (2023). Deep reinforcement learning for stock portfolio optimization by connecting with modern portfolio theory. Expert Systems with Applications, 218, 119556. https://doi.org/10.1016/j.eswa.2023.119556
  14. Jiang, Z., Xu, D. and Liang, J. (2017). A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059. https://doi.org/10.48550/arXiv.1706.10059
  15. Kochliaridis, V., Kouloumpris, E. and Vlahavas, I. (2023). Combining deep reinforcement learning with technical analysis and trend monitoring on cryptocurrency markets. Neural Computing and Applications, 35(29), 21445–21462. https://doi.org/10.1007/s00521-023-08516-x
  16. Liang, Z., Chen, H., Zhu, J., Jiang, K. and Li, Y. (2018). Adversarial deep reinforcement learning in portfolio management. arXiv preprint arXiv:1808.09940. https://doi.org/10.48550/arXiv.1808.09940
  17. Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D. and Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971. https://doi.org/10.48550/arXiv.1509.02971
  18. Lim, Q.Y.E., Cao, Q. and Quek, C. (2022). Dynamic portfolio rebalancing through reinforcement learning. Neural Computing and Applications, 34(9), 7125–7139. https://doi.org/10.1007/s00521-021-06853-3
  19. Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77–91. https://doi.org/10.2307/2975974
  20. Meng, T.L. and Khushi, M. (2019). Reinforcement learning in financial markets. Data, 4(3), 110. https://doi.org/10.3390/data4030110
  21. Merton, R.C. (1973). An intertemporal capital asset pricing model. Econometrica, 41(5), 867–887. https://doi.org/10.2307/1913811
  22. Michaud, R.O. (1989). The Markowitz optimization enigma: Is optimized optimal? Financial Analysts Journal, 45(1), 31–42. https://doi.org/10.2469/faj.v45.n1.31
  23. Moody, J. and Saffell, M. (2001). Learning to trade via direct reinforcement. IEEE Transactions on Neural Networks, 12(4), 875–889. https://doi.org/10.1109/72.935097
  24. Ozbayoglu, A.M., Gudelek, M.U. and Sezer, O. B. (2020). Deep learning for financial applications: A survey. Applied Soft Computing, 93, 106384. https://doi.org/10.1016/j.asoc.2020.106384
  25. Qian, E. (2011). Risk parity and diversification. Journal of Investing, 20(1), 119. Retrieved from https://www.panagora.com/
  26. Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M. and Dormann, N. (2021). Stable-Baselines3: Reliable reinforcement learning implementations. Journal of Machine Learning Research, 22(268), 1–8. Retrieved from https://jmlr.org
  27. Rjoub, H., Türsoy, T. and Günsel, N. (2009). The effects of macroeconomic factors on stock returns: Istanbul Stock Exchange. Studies in Economics and Finance, 26(1), 36–45. https://doi.org/10.1108/10867370910946315
  28. Rockafellar, R.T. and Uryasev, S. (2000). Optimization of conditional value-at-risk. Journal of Risk, 2(3), 21–41. Retrieved from https://sites.math.washington.edu
  29. Samuelson, P.A. (1969). Lifetime portfolio selection by dynamic stochastic programming. The Review of Economics and Statistics, 51(3), 239–246. https://doi.org/10.2307/1926559
  30. Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D. and Riedmiller, M. (2014). Deterministic policy gradient algorithms. In E. P. Xing and T. Jebara (Eds.), Proceedings of the 31st International Conference on Machine Learning (pp. 387–395). Retrieved from https://proceedings.mlr.press/
  31. Sun, R., Stefanidis, A., Jiang, Z. and Su, J. (2024). Combining transformer based deep reinforcement learning with Black-Litterman model for portfolio optimization. Neural Computing and Applications, 36(32), 20111–20146. https://doi.org/10.1007/s00521-024-09805-9
  32. Sutton, R.S. and Barto, A.G. (2018). Reinforcement learning: An introduction (2nd ed.). Cambridge: MIT Press.
  33. Sutton, R.S., McAllester, D.A., Singh, S.P. and Mansour, Y. (1999). Policy gradient methods for reinforcement learning with function approximation. Advances in Neural Information Processing Systems, 12, 1057–1063. Retrieved from https://proceedings.neurips.cc/
  34. Tversky, A. and Kahneman, D. (1974). Judgment under uncertainty: Heuristics and biases. Science, 185(4157), 1124–1131. Retrieved from https://www.jstor.org/
  35. Wang, H. and Zhou, X.Y. (2020). Continuous-time mean–variance portfolio selection: A reinforcement learning framework. Mathematical Finance, 30(4), 1273–1308. https://doi.org/10.48550/arXiv.1904.11392
  36. Williams, R.J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3), 229–256. https://doi.org/10.1007/BF00992696
  37. Yu, P., Lee, J.S., Kulyatin, I., Shi, Z. and Dasgupta, S. (2019). Model-based deep reinforcement learning for dynamic portfolio optimization. arXiv preprint arXiv:1901.08740. https://doi.org/10.48550/arXiv.1901.08740