{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T12:09:59Z","timestamp":1771502999018,"version":"3.50.1"},"reference-count":48,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:p>Recently, the algorithmic trading of financial assets is rapidly developing with the rise of deep learning. In particular, deep reinforcement learning, as a combination of deep learning and reinforcement learning, stands out among many approaches in the field of decision-making because of its high performance, strong generalization, and high fitting ability. In this paper, we attempt to propose a hybrid method of recurrent reinforcement learning (RRL) and deep learning to figure out the algorithmic trading problem of determining the optimal trading position in the daily trading activities of the stock market. We adopt deep neural network (DNN), long short-term memory neural network (LSTM), and bidirectional long short-term memory neural network (BiLSTM) to automatically extract higher-level abstract feature information from sequential trading data, respectively, and then generate optimal trading strategies by interacting with the environment in a reinforcement learning framework. In particular, the BiLSTM consisting of two LSTM models with opposite directions is able to make full use of the information from both directions in attempting to capture more effective information. In experiments, the daily data of Dow Jones, S&amp;P500, and NASDAQ (from Jan-01, 2005 to Dec-31, 2020) are applied to verify the performance of the newly proposed DNN-RL, LSTM-RL, and BiLSTM-RL trading systems. Experimental results show that the proposed methods significantly outperform the benchmark methods, such as RRL and Buy and Hold, with higher scalability and better robustness. Especially, BiLSTM-RL performs better than other methods.<\/jats:p>","DOI":"10.3233\/jifs-223101","type":"journal-article","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T12:19:59Z","timestamp":1684844399000},"page":"1939-1951","source":"Crossref","is-referenced-by-count":5,"title":["A new hybrid method of recurrent reinforcement learning and BiLSTM for algorithmic trading"],"prefix":"10.1177","volume":"45","author":[{"given":"Yuling","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Taipa, Macao, China"}]},{"given":"Yunlin","family":"Song","sequence":"additional","affiliation":[{"name":"School of Business, Macau University of Science and Technology, Taipa, Macao, China"}]}],"member":"179","reference":[{"issue":"1","key":"10.3233\/JIFS-223101_ref1","doi-asserted-by":"crossref","first-page":"48","DOI":"10.32629\/memf.v3i1.650","article-title":"Prediction and Analysis of Financial Volatility Based on Implied Volatility and GARCH Model","volume":"3","author":"Lin","year":"2022","journal-title":"Modern Economics & Management Forum"},{"issue":"1","key":"10.3233\/JIFS-223101_ref2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3390\/jrfm16010025","article-title":"The Effect of COVID-19 on Cryptocurrencies and the Stock Market Volatility: A Two-Stage DCC-EGARCH Model Analysis","volume":"16","author":"Ampountolas","year":"2023","journal-title":"Journal of Risk and Financial Management"},{"key":"10.3233\/JIFS-223101_ref3","doi-asserted-by":"crossref","first-page":"115149","DOI":"10.1016\/j.eswa.2021.115149","article-title":"A hybrid approach of adaptive wavelet transform, long short-term memory and ARIMA-GARCH family models for the stock index prediction","volume":"182","author":"Zolfaghari","year":"2021","journal-title":"Expert Systems with Applications"},{"issue":"11","key":"10.3233\/JIFS-223101_ref4","doi-asserted-by":"crossref","first-page":"2292","DOI":"10.3390\/sym14112292","article-title":"The Way to Invest: Trading Strategies Based on ARIMA and Investor Personality","volume":"14","author":"Tang","year":"2022","journal-title":"Symmetry"},{"key":"10.3233\/JIFS-223101_ref5","doi-asserted-by":"crossref","unstructured":"Rustam Z. , Vibranti D.F. and Widya D. , Predicting the direction of Indonesian stock price movement using support vector machines and fuzzy Kernel C-Means, Proceedings of the 3rd international symposium on current progress in mathematics and sciences 2017 (ISCPMS2017), 2017.","DOI":"10.1063\/1.5064205"},{"key":"10.3233\/JIFS-223101_ref6","doi-asserted-by":"crossref","unstructured":"Soni P. , Tewari Y. and Krishnan D. , Machine Learning Approaches in Stock Price Prediction: A Systematic Review, Journal of Physics: Conference Series 2161 (2022).","DOI":"10.1088\/1742-6596\/2161\/1\/012065"},{"key":"10.3233\/JIFS-223101_ref7","unstructured":"Sutton R.S. and Barto A.G. , Reinforcement Learning: An Introduction, Cambridge, MIT press, 2018."},{"issue":"7540","key":"10.3233\/JIFS-223101_ref8","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.3233\/JIFS-223101_ref9","doi-asserted-by":"crossref","unstructured":"Silver D. , Huang A. , Maddison C.J. , et al., Mastering the game of Go with deep neural networks and tree search, Nature, 2016.","DOI":"10.1038\/nature16961"},{"issue":"4","key":"10.3233\/JIFS-223101_ref10","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1109\/72.935097","article-title":"Learning to trade via direct reinforcement","volume":"12","author":"Moody","year":"2001","journal-title":"NaIEEE transactions on neural networksture"},{"key":"10.3233\/JIFS-223101_ref11","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/S1566-0141(00)00006-6","article-title":"Simple technical trading rules of stock returns: evidence from to in Chile","volume":"1","author":"Parisi","year":"2000","journal-title":"Emerging Markets Review"},{"key":"10.3233\/JIFS-223101_ref12","doi-asserted-by":"crossref","first-page":"101263","DOI":"10.1016\/j.frl.2019.08.011","article-title":"The profitability of technical trading rules in the Bitcoin market","volume":"34","author":"Gerritsen","year":"2020","journal-title":"Finance Research Letters"},{"key":"10.3233\/JIFS-223101_ref13","unstructured":"Persio L.D. and Honchar O. , Artificial neural networks architectures for stock price prediction, Comparisons and applications, 2016."},{"issue":"4","key":"10.3233\/JIFS-223101_ref14","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1007\/s11280-017-0495-4","article-title":"Tales of emotion and stock in China: volatility, causality and prediction","volume":"21","author":"Zhou","year":"2018","journal-title":"World Wide Web"},{"key":"10.3233\/JIFS-223101_ref15","doi-asserted-by":"crossref","unstructured":"Verma I. , Dey L. and Meisheri H. , Detecting, quantifying and accessing impact of news events on Indian stock indices, International Conference on Web Intelligence ACM, 2017.","DOI":"10.1145\/3106426.3106482"},{"issue":"4","key":"10.3233\/JIFS-223101_ref16","first-page":"1754","article-title":"Predicting stock prices using LSTM","volume":"6","author":"Roondiwala","year":"2017","journal-title":"International Journal of Science and Research (IJSR)"},{"key":"10.3233\/JIFS-223101_ref17","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/IACS.2018.8355458","article-title":"Evaluation of bidirectional LSTM for short-and long-term stock market prediction","author":"Althelaya","year":"2018","journal-title":"2018 9th international conference on information and communication systems (ICICS)"},{"issue":"6","key":"10.3233\/JIFS-223101_ref18","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1007\/s11280-018-0534-9","article-title":"Discovery of trading points based on Bayesian modeling of trading rules","volume":"21","author":"Huang","year":"2018","journal-title":"World Wide Web"},{"key":"10.3233\/JIFS-223101_ref19","doi-asserted-by":"crossref","first-page":"1970","DOI":"10.18653\/v1\/P18-1183","article-title":"Stock movement prediction from tweets and historical prices, pp. \u2013","author":"Xu","year":"2018","journal-title":"In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"},{"issue":"9","key":"10.3233\/JIFS-223101_ref20","doi-asserted-by":"crossref","first-page":"1507","DOI":"10.1080\/14697688.2019.1622287","article-title":"Exploring the attention mechanism in lstm-based hong kong stock price movement prediction","volume":"19","author":"Chen","year":"2019","journal-title":"Quantitative Finance"},{"issue":"1","key":"10.3233\/JIFS-223101_ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-020-00333-6","article-title":"Short-term stock market price trend prediction using a comprehensive deep learning system","volume":"7","author":"Shen","year":"2020","journal-title":"Journal of big Data"},{"key":"10.3233\/JIFS-223101_ref22","first-page":"1","article-title":"Prediction of stock price and direction using neural networks: Datasets hybrid modeling approach","author":"Al Aradi","year":"2020","journal-title":"2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI)"},{"key":"10.3233\/JIFS-223101_ref23","doi-asserted-by":"crossref","first-page":"5949","DOI":"10.3233\/JIFS-179681","article-title":"A deep learning based hybrid framework for stock price prediction","volume":"38","author":"Mundra","year":"2020","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.3233\/JIFS-223101_ref24","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/NILES50944.2020.9257950","article-title":"Deep learning-based stock price prediction using LSTM and bi-directional LSTM model","author":"Sunny","year":"2020","journal-title":"In 2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)"},{"key":"10.3233\/JIFS-223101_ref25","first-page":"1","article-title":"Stock Market Prediction using Bi-Directional LSTM","author":"Shah","year":"2021","journal-title":"2021 International Conference on Communication information and Computing Technology (ICCICT)"},{"key":"10.3233\/JIFS-223101_ref26","doi-asserted-by":"crossref","first-page":"115378","DOI":"10.1016\/j.eswa.2021.115378","article-title":"Forecasting cryptocurrency price using convolutional neural networks with weighted and attentive memory channels","volume":"183","author":"Zhang","year":"2021","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"10.3233\/JIFS-223101_ref27","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1007\/s11280-021-00880-9","article-title":"A hybrid approach for stock trend prediction based on tweets embedding and historical prices","volume":"24","author":"Ni","year":"2021","journal-title":"World Wide Web"},{"key":"10.3233\/JIFS-223101_ref28","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.procs.2022.01.003","article-title":"Adaptability of Financial Time Series Prediction Based on BiLSTM","volume":"199","author":"Yang","year":"2022","journal-title":"Procedia Computer Science"},{"key":"10.3233\/JIFS-223101_ref29","doi-asserted-by":"crossref","first-page":"13267","DOI":"10.1007\/s00521-021-06828-4","article-title":"Applying attention-based BiLSTM and technical indicators in the design and performance analysis of stock trading strategies","volume":"34","author":"Lee","year":"2022","journal-title":"Neural Computing & Applications"},{"key":"10.3233\/JIFS-223101_ref30","first-page":"1","article-title":"Forecasting Directional Movement of Stock Prices using Deep Learning","author":"Chandola","year":"2022","journal-title":"Annals of Data Science"},{"key":"10.3233\/JIFS-223101_ref31","doi-asserted-by":"crossref","unstructured":"Md A.Q. , Kapoor S. , A.V. C.J. , Sivaraman A.K. , Tee K.F. S.H., and J.N., Novel optimization approach for stock price forecasting using multi-layered sequential LSTM, Applied Soft Computing, 2022.","DOI":"10.1016\/j.asoc.2022.109830"},{"key":"10.3233\/JIFS-223101_ref32","doi-asserted-by":"crossref","unstructured":"Bhandari H.N. , Rimal B. , Pokhrel N.R. , Rimal R. , Dahal K.R. and Khatri R.K. , Predicting stock market index using LSTM, Machine Learning with Applications, 2022.","DOI":"10.1016\/j.mlwa.2022.100320"},{"issue":"3","key":"10.3233\/JIFS-223101_ref33","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/TNNLS.2016.2522401","article-title":"Deep Direct Reinforcement Learning for Financial Signal Representation and Trading","volume":"28","author":"Deng","year":"2017","journal-title":"In IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.3233\/JIFS-223101_ref34","unstructured":"Lu David W. , Agent inspired trading using recurrent reinforcement learning and lstm neural networks, arXiv preprint arXiv:1707.07338, 2017."},{"key":"10.3233\/JIFS-223101_ref35","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.eswa.2017.06.023","article-title":"An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown","volume":"87","author":"Almahdi","year":"2017","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-223101_ref36","doi-asserted-by":"crossref","first-page":"112891","DOI":"10.1016\/j.eswa.2019.112891","article-title":"Continuous control with stacked deep dynamic recurrent reinforcement learning for portfolio optimization","volume":"140","author":"Aboussalah","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-223101_ref37","doi-asserted-by":"crossref","unstructured":"Nguyen H.T. and Luong N.H. , Applying Deep Reinforcement Learning in Automated Stock Trading, pp. 285\u2013 297, In Soft Computing: Biomedical and Related Applications, 2021.","DOI":"10.1007\/978-3-030-76620-7_25"},{"key":"10.3233\/JIFS-223101_ref38","doi-asserted-by":"crossref","unstructured":"Li F. , Wang Z. and Zhou P. , Ensemble Investment Strategies Based on Reinforcement Learning, Scientific Programming, 2022.","DOI":"10.1155\/2022\/7648810"},{"key":"10.3233\/JIFS-223101_ref39","doi-asserted-by":"crossref","unstructured":"Ge J. , Qin Y. , Li Y. , Huang Y. and Hu H. , Single stock trading with deep reinforcement learning: A comparative study, 2022 14th International Conference on Machine Learning and Computing (ICMLC), 2022.","DOI":"10.1145\/3529836.3529857"},{"key":"10.3233\/JIFS-223101_ref40","doi-asserted-by":"crossref","unstructured":"Li Y. , Liu P. and Wang Z. , Stock Trading Strategies Based on Deep Reinforcement Learning, Scientific Programming, 2022.","DOI":"10.1155\/2022\/4698656"},{"key":"10.3233\/JIFS-223101_ref41","unstructured":"Zou J. , Lou J. , Wang B. and Liu S. , A Novel Deep Reinforcement Learning Based Automated Stock Trading System Using Cascaded LSTM Networks, ArXiv, abs\/2212.02721, 2022."},{"key":"10.3233\/JIFS-223101_ref42","doi-asserted-by":"crossref","unstructured":"Malibari N. , Katib I.A. and Mehmood R. , Smart Robotic Strategies and Advice for Stock Trading Using Deep Transformer Reinforcement Learning, Applied Sciences, 2022.","DOI":"10.3390\/app122412526"},{"key":"10.3233\/JIFS-223101_ref43","first-page":"1151","article-title":"Research on investment strategies of stock market based on sentiment indicators and deep reinforcement learning","volume":"12163","author":"Zhou","year":"2022","journal-title":"In International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021)"},{"key":"10.3233\/JIFS-223101_ref44","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1515\/9781400829408-022","article-title":"The sharpe ratio, the Best of the Journal of Portfolio Management","author":"Sharpe","year":"1998","journal-title":"Streetwise \u2013 the Best of the Journal of Portfolio Management"},{"issue":"8","key":"10.3233\/JIFS-223101_ref45","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural computation"},{"issue":"11","key":"10.3233\/JIFS-223101_ref46","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE transactions on Signal Processing"},{"issue":"5-6","key":"10.3233\/JIFS-223101_ref47","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Networks"},{"issue":"8","key":"10.3233\/JIFS-223101_ref48","doi-asserted-by":"crossref","first-page":"178","DOI":"10.3390\/jrfm13080178","article-title":"Cryptocurrency trading using machine learning","volume":"13","author":"Koker","year":"2020","journal-title":"Journal of Risk and Financial Management"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-223101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T09:23:31Z","timestamp":1769678611000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-223101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,1]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-223101","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,1]]}}}