دانشگاه تربیت دبیر شهید رجائی
انتشارات دانشگاه تربیت دبیر شهید رجائی

  اخبار و اعلانات

 آمار

تعداد نشریات11
تعداد شماره‌ها210
تعداد مقالات2,098
تعداد مشاهده مقاله2,877,853
تعداد دریافت فایل اصل مقاله2,085,737
Khonsha, S., Sarram, M., Sheikhpour, R.. (1403). A Robust Concurrent Multi-Agent Deep Reinforcement Learning ‎based Stock Recommender System. فناوری آموزش, 13(1), 225-240. doi: 10.22061/jecei.2024.11193.775
S. Khonsha; M. A. Sarram; R. Sheikhpour. "A Robust Concurrent Multi-Agent Deep Reinforcement Learning ‎based Stock Recommender System". فناوری آموزش, 13, 1, 1403, 225-240. doi: 10.22061/jecei.2024.11193.775
Khonsha, S., Sarram, M., Sheikhpour, R.. (1403). 'A Robust Concurrent Multi-Agent Deep Reinforcement Learning ‎based Stock Recommender System', فناوری آموزش, 13(1), pp. 225-240. doi: 10.22061/jecei.2024.11193.775
Khonsha, S., Sarram, M., Sheikhpour, R.. A Robust Concurrent Multi-Agent Deep Reinforcement Learning ‎based Stock Recommender System. فناوری آموزش, 1403; 13(1): 225-240. doi: 10.22061/jecei.2024.11193.775

A Robust Concurrent Multi-Agent Deep Reinforcement Learning ‎based Stock Recommender System

Journal of Electrical and Computer Engineering Innovations (JECEI)
مقاله 18، دوره 13، شماره 1، فروردین 2025، صفحه 225-240    اصل مقاله (1.89 M)
نوع مقاله: Original Research Paper
شناسه دیجیتال (DOI): 10.22061/jecei.2024.11193.775
نویسندگان
S. Khonsha1؛ M. A. Sarram2؛ R. Sheikhpour* 3
1Department of Computer Engineering, Zarghan Branch, Islamic Azad University, Zarghan, Iran.
2Computer Engineering Department, Yazd University, Yazd, Iran. ‎
3Department of Computer Engineering, Faculty of Engineering, Ardakan University, P.O. Box 184, Ardakan, Iran.
تاریخ دریافت: 31 مرداد 1403،  تاریخ بازنگری: 14 آبان 1403،  تاریخ پذیرش: 27 آبان 1403 
چکیده
Background and Objectives: Stock recommender system (SRS) based on deep ‎reinforcement learning (DRL) has garnered significant attention within the ‎financial research community. A robust DRL agent aims to consistently ‎allocate some amount of cash to the combination of high-risk and low-risk ‎stocks with the ultimate objective of maximizing returns and balancing risk. ‎However, existing DRL-based SRSs focus on one or, at most, two sequential ‎trading agents that operate within the same or shared environment, and ‎often make mistakes in volatile or variable market conditions. In this paper, ‎a robust Concurrent Multiagent Deep Reinforcement Learning-based Stock ‎Recommender System (CMSRS) is proposed.‎
Methods: The proposed system introduces a multi-layered architecture that ‎includes feature extraction at the data layer to construct multiple trading ‎environments, so that different feed DRL agents would robustly recommend ‎assets for trading layer.‎‏ ‏The proposed CMSRS uses a variety of data sources, ‎including Google stock trends, fundamental data and technical indicators ‎along with historical price data, for the selection and recommendation ‎suitable stocks to buy or sell concurrently by multiple agents. To optimize ‎hyperparameters during the validation phase, we employ Sharpe ratio as a ‎risk adjusted return measure. Additionally, we address liquidity ‎requirements by defining a precise reward function that dynamically ‎manages cash reserves. We also penalize the model for failing to maintain a ‎reserve of cash.‎
Results: The empirical results on the real U.S. stock market data show the ‎superiority of our CMSRS, especially in volatile markets and out-of-sample ‎data.‎
Conclusion: The proposed CMSRS demonstrates significant advancements in ‎stock recommendation by effectively leveraging multiple trading agents and ‎diverse data sources. The empirical results underscore its robustness and ‎superior performance, particularly in volatile market conditions. This multi-‎layered approach not only optimizes returns but also efficiently manages ‎risks and liquidity, offering a compelling solution for dynamic and uncertain ‎financial environments. Future work could further refine the model's ‎adaptability to other market conditions and explore its applicability across ‎different asset classes.‎
کلیدواژه‌ها
Multi-Agent؛ Concurrent Learning؛ Deep Reinforcement Learning؛ ‎Stock Recommender System ‎
مراجع

[1] M. Z. Asghar, F. Rahman, F. M. Kundi, S. Ahmad, "Development of stock market trend prediction system using multiple regression," Comput. Math. Organ. Theory, 25(2019): 271-301, 2019.

[2] A. A. Ariyo, A. O. Adewumi, C. K. Ayo, "Stock price prediction using the ARIMA model," in Proc. 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation: 106-112, 2014.

[3] Y. Wang, Y. Liu, M. Wang, R. Liu, “LSTM model optimization on stock price forecasting,” in Proc. 2018 17th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES): 173-177, 2018.

[4] S. Banik, N. Sharma, M. Mangla, S. N. Mohanty, S. Shitharth, “LSTM based decision support system for swing trading in stock market,” Knowl. Based Syst., 239: 107994, 2022.

[5] S. Selvin, R. Vinayakumar, E. A. Gopalakrishnan, V. K. Menon, K. P. Soman, “Stock price prediction using LSTM, RNN and CNN-sliding window model,” in Proc. 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI): 1643-1647, 2017.

[6] V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness et al., “Human-level control through deep reinforcement learning,” Nature, 518(7540): 529-533, 2015.

[7] D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifreet al., “Mastering the game of Go with deep neural networks and tree search,” Nature, 529 (7587): 484-489, 2016.

[8] A. R. Azhikodan, A. G. Bhat, M. V. Jadhav, “Stock trading bot using deep reinforcement learning,” in Innovations in Computer Science and Engineering, Proc. the Fifth ICICSE 2017: 41-49, Springer, 2019.

[9] X. Wu, H. Chen, J. Wang, L. Troiano, V. Loia, H. Fujita, “ Adaptive stock trading strategies with deep reinforcement learning methods,” Inf. Sci., 538: 142-158, 2020.

[10] S. Carta, A. Corriga, A. Ferreira, A. S. Podda, D. R. Recupero, “A multi-layer and multi-ensemble stock trader using deep learning and deep reinforcement learning,” Appl. Intell., 51: 889-905, 2021.

[11] X. Y. Liu, H. Yang, Q. Chen, R. Zhang, L. Yang, B. Xiao, C. D. Wang, “FinRL: A deep reinforcement learning library for automated stock trading in quantitative finance,” arXiv preprint arXiv:2011.09607, 2020.

[12] S. Yang, “Deep reinforcement learning for portfolio management,” Knowl. Based Syst., 278: 110905, 2023.

‎[13] C. Ma, J. Zhang, Z. Li, S. Xu, “Multi-agent deep reinforcement learning algorithm with trend consistency regularization for ‎portfolio management,” Neural Comput. Appl., 35(9): 6589-6601, 2023.‎

[14] Z. Huang, F. Tanaka, “MSPM: A modularized and scalable multi-agent reinforcement learning-based system for financial portfolio management,” Plos one, 17(2): e0263689, 2022.

[15] J. Lussange, I. Lazarevich, S. Bourgeois-Gironde, S. Palminteri, B. Gutkin, “Modelling stock markets by multi-agent reinforcement learning,” Comput. Econ., 57: 113-147, 2021.

[16] J. Lee, R. Kim, S. W. Yi, J. Kang, “MAPS: Multi-agent reinforcement learning-based portfolio management system,” arXiv preprint arXiv:2007.05402, 2020.

[17] P. Koratamaddi, K. Wadhwani, M. Gupta, D. S. G. Sanjeevi, “A multi-agent reinforcement learning approach for stock portfolio allocation,” in Proc. the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD): 410-410, 2021.

‎[18] D. Kwak, S. Choi, W. Chang, “Self-attention based deep direct recurrent reinforcement learning with hybrid loss for trading signal ‎generation,” Inf. Sci., 623: 592-606, 2023.‎

[19] S. Forouzandeh, K. Berahmand, R. Sheikhpour, Y. Li, “A new method for recommendation based on embedding spectral clustering in heterogeneous networks (RESCHet),” Expert Syst. Appl., 231: 120699, 2023.‎

‎[20] S. Forouzandeh, M. Rostami, K. Berahmand, R. Sheikhpour, “Health-aware food recommendation system with dual ‎attention in heterogeneous graphs,” Comput. Biol. ‎Med., 169: 107882, 2024.‎

[21] M. Nourahmadi, A. Rahimi, H. Sadeqi, “Designing a ‎stock recommender system using the collaborative filtering ‎algorithm for the Tehran stock exchange,” Financ. Res. ‎J., 26(2): 302-330, 2024‎.

[22] B. Yang, T. Liang, J. Xiong, C. Zhong, “Deep reinforcement learning based on transformer and U-Net framework for stock trading,” Knowl. Based Syst., 262: 110211, 2023.

[23] J. Zou, J. Lou, B. Wang, S. Liu, “A novel deep reinforcement learning based automated stock trading system using cascaded lstm networks,” Expert Syst. Appl., 242: 122801, 2024.

[24] F. F. He, C. T. Chen, S. H. Huang, “A multi-agent virtual market model for generalization in reinforcement learning based trading strategies,” Appl. Soft Comput., 134, 109985, 2023.

[25] S. Singh, V. Goyal, S. Goel, H. C. Taneja, “Deep reinforcement learning models for automated stock trading," in Advanced Production and Industrial Engineering, 27: 175, 2022.

[26] M. Taghian, A. Asadi, R. Safabakhsh, “Learning financial asset-specific trading rules via deep reinforcement learning,” Expert Syst. Appl., 195: 116523, 2022.

[27] L. K. Felizardo, F. C. L. Paiva, C. de Vita Graves, E. Y. Matsumoto, A. H. R. Costa, E. Del-Moral-Hernandez, P. Brandimarte, “Outperforming algorithmic trading reinforcement learning systems: A supervised approach to the cryptocurrency market,” Expert Syst. Appl., 202: 117259, 2022.

[28] R. S. Sutton, A. G. Barto, Reinforcement learning: An introduction, MIT press, 2018.

[29] T. Faturohman, T. Nugraha, “Islamic stock portfolio optimization using deep reinforcement learning,” J. Islamic Monetary Econ. Finance, 8(2): 181-200, 2022.

[30] H. Yue, J. Liu, D. Tian, Q. Zhang, “A novel anti-risk method for portfolio trading using deep reinforcement learning,” Electronics, 11(9): 1506, 2022.

[31] A. Nair, P. Srinivasan, S. Blackwell, C. Alcicek, R. Fearon, A. De Maria et al., “Massively parallel methods for deep reinforcement learning,” arXiv preprint arXiv:1507.04296, 2015.

[32] Y. Shoham, K. Leyton-Brown, “Multiagent systems: Algorithmic, game-theoretic, and logical foundations,” Cambridge University Press, 2008.

[33] R. Lowe, Y. I. Wu, A. Tamar, J. Harb, O. Pieter Abbeel, I. Mordatch, “Multi-agent actor-critic for mixed cooperative-ompetitive environments,” Adv. Neural Inf. Processing Syst., 30, 2017.

[34] S. Khonsha, M. A. Sarram, R. Sheikhpour, “A profitable portfolio allocation strategy based on money net-flow adjusted deep reinforcement learning,” Iran. J. Finance, 7(4): 59-89, 2023.

[35] H. Hu, L. Tang, S. Zhang, H. Wang, “Predicting the ‎direction of stock markets using optimized neural networks with ‎Google Trends,” Neurocomput., 285: 188-195, 2018.

[36] J. Schulman, F. ‎Wolski, P. Dhariwal, A. Radford, O. Klimov, “‎Proximal policy optimization algorithms,” arXiv preprint ‎arXiv:1707.06347, 2018.‎

آمار
تعداد مشاهده مقاله: 96
تعداد دریافت فایل اصل مقاله: 81


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب