Enhanced reinforcement learning based on trend line for trading decisions on cryptocurrency
,
,
and
Article Sidebar
Full Text: 
PDF
Abstract
The use of a machine learning algorithm in combination with the data on cryptocurrency market price trends to make buying and selling decisions is studied in this paper. We suggest that agents combined with data trends should be used to make financial decisions instead of just using reinforcement learning. The research question is to answer the problem that can reinforcement learning (RL) win the financial market? RL that makes market-based buying and selling decisions can win in terms of profitability and limit risks? Results suggest that agents combined with data trends should be used to make financial decisions instead of just using reinforcement learning. Various financial indicators are applied such as Maximum Drawdown, Annual Profit, and Accuracy. Analysis results are conducted on two datasets of Bitcoin and Dogecoin, finding that the RL based on the trendline has more advantages than the RL without the trendline based on different performance indicators.
Tóm tắt
Việc dùng thuật toán máy học với sự kết hợp dữ liệu đường xu hướng giá của thị trường tiền điện tử để ra quyết định mua bán được nghiên cứu trong bài viết. Thay vì chỉ sử dụng mô hình học tăng cường để thực thi hành động trong môi trường tài chính, học tăng cường kết hợp với xu hướng dữ liệu để ra quyết định hành động. Nghiên cứu trả lời cho câu hỏi dùng học tăng cường có thể chiến thắng được thị trường tài chính hay không? Học tăng cường tự ra các quyết định mua bán dựa trên thị trường có mang lại lợi nhuận cho nhà đầu tư, giúp giảm rủi ro đầu tư hay không? Kết quả nghiên cứu cho thấy các tác nhân được kết hợp với xu hướng dữ liệu nên được dùng để ra quyết định tài chính thay vì chỉ sử dụng học tăng cường. Các thước đo tài chính về mức sụt giảm tối đa, lợi nhuận hằng năm, độ chính xác được dùng để đánh giá. Kết quả phân tích được thực hiện trên hai tập dữ liệu là Dogecoin và Bitcoin chỉ ra thuật toán học tăng cường dựa trên đường xu hướng có ưu điểm hơn so với học tăng cường không theo đường xu hướng trong các khía cạnh sử dụng chỉ số đánh giá hiệu năng khác nhau.
Article Details
References
Braham, R., Samad, M.E., Bakhach, A.M., El-Chaarani, H., Sardouk, A., Nemar, S.E. & Jaber, D. (2022). Forecasting a Stock Trend Using Genetic Algorithm and Random Forest. J. Risk Financial Manag. 15, 188. https://doi.org/10.3390/jrfm15050188.
Cao, L. (2021). AI in Finance: Challenges, Techniques, and Opportunities. ACM Computing Surveys (CSUR) 55: 1 - 38. https://doi.org/10.48550/arXiv.2107.09051
Cao, L. (July 10, 2020). AI in Finance: A Review Available at SSRN https://ssrn.com/abstract=3647625 or http://dx.doi.org/10.2139/ssrn.3647625
Carta, S., Ferreira, A., Podda, A.S., Recupero, D.R., & Sanna, A. (2020). Multi-DQN: an
Ensemble of Deep Q-Learning Agents for Stock Market Forecasting, Expert Systems with Applications. doi: https://doi.org/10.1016/j.eswa.2020.113820
Chopra, R., & Sharma, G.D. (2021). Application of Artificial Intelligence in Stock Market Forecasting: A Critique, Review, and Research Agenda. J. Risk Financial Manag., 14, 526. https://doi.org/10.3390/jrfm14110526
Culkin, R. (2017). Machine Learning in Finance: The Case of Deep Learning for Option Pricing.
Fischer, T. G. (2018). Reinforcement learning in financial markets - a survey. Economics.
Jagdish, C., & Manish, K.. (2019). Trend following deep Q-Learning strategy for stock trading. Expert Systems. https://doi.org/10.1111/exsy.12514
Kabbani, T., & Ekrem D. (2022). Deep Reinforcement Learning Approach for Trading Automation in the Stock Market. IEEE Access. 10: 93564-93574. https://doi.org/10.48550/arXiv.2208.07165
Li, Y. (2017). Deep Reinforcement Learning: An Overview. ArXiv abs/1701.07274.
Mhlanga, D. (2020). Industry 4.0 in Finance: The Impact of Artificial Intelligence (AI) on Digital Financial Inclusion. Int. J. Financial Stud., 8, 45. https://doi.org/10.3390/ijfs8030045
Jay, P., Kalariya, V., Parmar, P., Tanwar, S., Kumar, N. & Alazab, M. (2020). Stochastic Neural Networks for Cryptocurrency Price Prediction. IEEE Access. vol. 8, pp. 82804-82818, doi: 10.1109/ACCESS.2020.2990659.
OECD (2021). Artificial Intelligence, Machine Learning and Big Data in Finance: Opportunities, Challenges, and Implications for Policy Makers, https://www.oecd.org/finance/artificial-intelligence-machine-learningbig-data-in-finance.htm.
Olorunnimbe, K., & Viktor, H. (2022). Deep learning in the stock market—a systematic survey of practice, backtesting, and applications. Artif Intell Rev. https://doi.org/10.1007/s10462-022-10226-0.
Shah, D., Isah, H. & Zulkernine, F. (2019). Stock Market Analysis: A Review and Taxonomy of Prediction Techniques. Int. J. Financial Stud. 7, 26. https://doi.org/10.3390/ijfs7020026
Shahi, T.B., Shrestha, A., Neupane, A. & Guo, W. (2020). Stock Price Forecasting with Deep Learning: A Comparative Study. Mathematics, 8, 1441. https://doi.org/10.3390/math8091441.
Singh, J. & Khushi, M. (2021). Feature Learning for Stock Price Prediction Shows a Significant Role of Analyst Rating. Appl. Syst. Innov., 4, 17. https://doi.org/10.3390/asi4010017.
Al-Sulaiman, T. (2022). Predicting reactions to anomalies in stock movements using a feed-forward deep learning network. International Journal of Information Management Data Insights, Volume 2, Issue 1, https://doi.org/10.1016/j.jjimei.2022.100071.
TOAI, T.K., HANH, V. T. X., HUAN, & V. M. (2022). Applying ridge regression
and ANN to predict ICO price after six months. Journal of Science.
TOAI, T. K.; SENKERIK, R.; ZELINKA, I.; ULRICH, A.; HANH, V.T. X.; & HUAN, V. M. (2022). ARIMA for Short-Term and LSTM for Long-Term in Daily Bitcoin Price Prediction. ICAISC2022 https://doi.org/10.1007/978-3-031-23492-7_12
Tsung-Jung, H., Hsiao-Fen, H., & Wei-Chang, Y. (2011). Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm. Applied Soft Computing. Volume 11, Issue 2, Pages 2510-2525. https://doi.org/10.1016/j.asoc.2010.09.007.
Deng, Y., Bao, F., Kong, Y., Ren, Z. & Dai, Q. (2017). Deep Direct Reinforcement Learning for Financial Signal Representation and Trading. IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 3, pp. 653-664. doi: 10.1109/TNNLS.2016.2522401.
Yang, H., Liu, X. Y., Zhong, S. & Walid, A. (2020). Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy. Available at SSRN:
https://ssrn.com/abstract=3690996 or http://dx.doi.org/10.2139/ssrn.3690996
Yuan, Q., & Jing, X. (2018). Fintech: AI powers financial services to improve people's lives. Commun. ACM 61, 11, 65–69. https://doi.org/10.1145/3239550.
Yuxuan, H., Luiz Fernando, C. & Danny, Ho. (2021). Machine Learning for Stock Prediction Based on Fundamental Analysis. 2021 IEEE Symposium Series on Computational Intelligence.