{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T18:55:49Z","timestamp":1778525749319,"version":"3.51.4"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"29","license":[{"start":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T00:00:00Z","timestamp":1681948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T00:00:00Z","timestamp":1681948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006470","name":"Aristotle University of Thessaloniki","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006470","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Cryptocurrency markets experienced a significant increase in the popularity, which motivated many financial traders to seek high profits in cryptocurrency trading. The predominant tool that traders use to identify profitable opportunities is technical analysis. Some investors and researchers also combined technical analysis with machine learning, in order to forecast upcoming trends in the market. However, even with the use of these methods, developing successful trading strategies is still regarded as an extremely challenging task. Recently, deep reinforcement learning (DRL) algorithms demonstrated satisfying performance in solving complicated problems, including the formulation of profitable trading strategies. While some DRL techniques have been successful in increasing profit and loss (PNL) measures, these techniques are not much risk-aware and present difficulty in maximizing PNL and lowering trading risks simultaneously. This research proposes the combination of DRL approaches with rule-based safety mechanisms to both maximize PNL returns and minimize trading risk. First, a DRL agent is trained to maximize PNL returns, using a novel reward function. Then, during the exploitation phase, a rule-based mechanism is deployed to prevent uncertain actions from being executed. Finally, another novel safety mechanism is proposed, which considers the actions of a more conservatively trained agent, in order to identify high-risk trading periods and avoid trading. Our experiments on 5 popular cryptocurrencies show that the integration of these three methods achieves very promising results.<\/jats:p>","DOI":"10.1007\/s00521-023-08516-x","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T19:46:19Z","timestamp":1682019979000},"page":"21445-21462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Combining deep reinforcement learning with technical analysis and trend monitoring on cryptocurrency markets"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9431-6679","authenticated-orcid":false,"given":"Vasileios","family":"Kochliaridis","sequence":"first","affiliation":[]},{"given":"Eleftherios","family":"Kouloumpris","sequence":"additional","affiliation":[]},{"given":"Ioannis","family":"Vlahavas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,20]]},"reference":[{"key":"8516_CR1","unstructured":"Nakamoto S (2008) Bitcoin: a peer-to-peer electronic cash system. Decent Bus Rev 21260"},{"issue":"1","key":"8516_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40854-021-00321-6","volume":"8","author":"F Fang","year":"2022","unstructured":"Fang F et al (2022) Cryptocurrency trading: a comprehensive survey. Financ Innov 8(1):1\u201359. https:\/\/doi.org\/10.1186\/s40854-021-00321-6","journal-title":"Financ Innov"},{"key":"8516_CR3","first-page":"678","volume":"60","author":"TC Lin","year":"2012","unstructured":"Lin TC (2012) The new investor. UCLA L Rev 60:678","journal-title":"UCLA L Rev"},{"issue":"23","key":"8516_CR4","doi-asserted-by":"publisher","first-page":"20715","DOI":"10.3390\/app10041506","volume":"34","author":"A Guarino","year":"2022","unstructured":"Guarino A, Grilli L, Santoro D, Messina F, Zaccagnino R (2022) To learn or not to learn? Evaluating autonomous, adaptive, automated traders in cryptocurrencies financial bubbles. Neural Comput Appl 34(23):20715\u201320756. https:\/\/doi.org\/10.3390\/app10041506","journal-title":"Neural Comput Appl"},{"issue":"1","key":"8516_CR5","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s42786-021-00027-4","volume":"5","author":"A Arratia","year":"2021","unstructured":"Arratia A, L\u00f3pez-Barrantes AX (2021) Do google trends forecast bitcoins? Stylized facts and statistical evidence. J Bank Financ Technol 5(1):45\u201357. https:\/\/doi.org\/10.1007\/s42786-021-00027-4","journal-title":"J Bank Financ Technol"},{"issue":"4","key":"8516_CR6","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.3390\/app10041506","volume":"10","author":"O Sattarov","year":"2020","unstructured":"Sattarov O et al (2020) Recommending cryptocurrency trading points with deep reinforcement learning approach. Appl Sci 10(4):1506. https:\/\/doi.org\/10.3390\/app10041506","journal-title":"Appl Sci"},{"issue":"3","key":"8516_CR7","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1016\/j.ejor.2021.04.050","volume":"296","author":"M Schnaubelt","year":"2022","unstructured":"Schnaubelt M (2022) Deep reinforcement learning for the optimal placement of cryptocurrency limit orders. Eur J Oper Res 296(3):993\u20131006. https:\/\/doi.org\/10.1016\/j.ejor.2021.04.050","journal-title":"Eur J Oper Res"},{"key":"8516_CR8","first-page":"304","volume-title":"Tradernet-cr: cryptocurrency trading with deep reinforcement learning","author":"V Kochliaridis","year":"2022","unstructured":"Kochliaridis V, Kouloumpris E, Vlahavas I (2022) Tradernet-cr: cryptocurrency trading with deep reinforcement learning. Springer, Berlin, pp 304\u2013315"},{"issue":"3","key":"8516_CR9","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.jfds.2018.10.001","volume":"5","author":"J-Z Huang","year":"2019","unstructured":"Huang J-Z, Huang W, Ni J (2019) Predicting bitcoin returns using high-dimensional technical indicators. J Finance Data Sci 5(3):140\u2013155","journal-title":"J Finance Data Sci"},{"key":"8516_CR10","doi-asserted-by":"crossref","unstructured":"Mahayana D, Shan E, Fadhl\u2019Abbas M (2022) Deep reinforcement learning to automate cryptocurrency trading, pp 36\u201341. IEEE","DOI":"10.1109\/ICSET57543.2022.10010940"},{"issue":"3","key":"8516_CR11","doi-asserted-by":"publisher","first-page":"103247","DOI":"10.1016\/j.ipm.2022.103247","volume":"60","author":"J Li","year":"2023","unstructured":"Li J, Zhang Y, Yang X, Chen L (2023) Online portfolio management via deep reinforcement learning with high-frequency data. Inf Process Manag 60(3):103247","journal-title":"Inf Process Manag"},{"issue":"23","key":"8516_CR12","doi-asserted-by":"publisher","first-page":"17229","DOI":"10.1007\/s00521-020-05359-8","volume":"32","author":"G Lucarelli","year":"2020","unstructured":"Lucarelli G, Borrotti M (2020) A deep Q-learning portfolio management framework for the cryptocurrency market. Neural Comput Appl 32(23):17229\u201317244. https:\/\/doi.org\/10.1007\/s00521-020-05359-8","journal-title":"Neural Comput Appl"},{"key":"8516_CR13","doi-asserted-by":"publisher","first-page":"106078","DOI":"10.1016\/j.econmod.2022.106078","volume":"119","author":"T Cui","year":"2023","unstructured":"Cui T, Ding S, Jin H, Zhang Y (2023) Portfolio constructions in cryptocurrency market: a CVaR-based deep reinforcement learning approach. Econ Model 119:106078","journal-title":"Econ Model"},{"key":"8516_CR14","volume-title":"Technical analysis explained","author":"MJ Pring","year":"1991","unstructured":"Pring MJ (1991) Technical analysis explained. McGraw-Hill, New York"},{"key":"8516_CR15","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"key":"8516_CR16","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1613\/jair.1.12412","volume":"69","author":"A Lazaridis","year":"2020","unstructured":"Lazaridis A, Fachantidis A, Vlahavas I (2020) Deep reinforcement learning: a state-of-the-art walkthrough. J Artif Intell Res 69:1421\u20131471. https:\/\/doi.org\/10.1613\/jair.1.12412","journal-title":"J Artif Intell Res"},{"key":"8516_CR17","doi-asserted-by":"publisher","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. https:\/\/doi.org\/10.48550\/ARXIV.1707.06347","DOI":"10.48550\/ARXIV.1707.06347"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08516-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08516-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08516-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T14:05:21Z","timestamp":1694873121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08516-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,20]]},"references-count":17,"journal-issue":{"issue":"29","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["8516"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08516-x","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,20]]},"assertion":[{"value":"30 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}