{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:04:12Z","timestamp":1782407052193,"version":"3.54.5"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T00:00:00Z","timestamp":1577059200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T00:00:00Z","timestamp":1577059200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"VC Research","award":["VCR 000005"],"award-info":[{"award-number":["VCR 000005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s00607-019-00773-w","type":"journal-article","created":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T09:03:30Z","timestamp":1577091810000},"page":"1305-1322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":106,"title":["Application of deep reinforcement learning in stock trading strategies and stock forecasting"],"prefix":"10.1007","volume":"102","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2219-9033","authenticated-orcid":false,"given":"Yuming","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-1249","authenticated-orcid":false,"given":"Pin","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8012-5852","authenticated-orcid":false,"given":"Victor","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,12,23]]},"reference":[{"key":"773_CR1","doi-asserted-by":"crossref","unstructured":"Abtahi F, Zhu Z, Burry AM (2015) A deep reinforcement learning approach to character segmentation of license plate images. In: 2015 14th IAPR international conference on machine vision applications (MVA), pp 539\u2013542. IEEE","DOI":"10.1109\/MVA.2015.7153249"},{"key":"773_CR2","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1016\/j.asoc.2018.03.051","volume":"68","author":"MR Alimoradi","year":"2018","unstructured":"Alimoradi MR, Kashan AH (2018) A league championship algorithm equipped with network structure and backward q-learning for extracting stock trading rules. Appl Soft Comput 68:478\u2013493","journal-title":"Appl Soft Comput"},{"key":"773_CR3","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.eswa.2017.06.023","volume":"87","author":"S Almahdi","year":"2017","unstructured":"Almahdi S, Yang SY (2017) An adaptive portfolio trading system: a risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Syst Appl 87:267\u2013279","journal-title":"Expert Syst Appl"},{"key":"773_CR4","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.eswa.2015.10.040","volume":"46","author":"JM Berutich","year":"2016","unstructured":"Berutich JM, L\u00f3pez F, Luna F, Quintana D (2016) Robust technical trading strategies using gp for algorithmic portfolio selection. Expert Syst Appl 46:307\u2013315","journal-title":"Expert Syst Appl"},{"issue":"5","key":"773_CR5","doi-asserted-by":"publisher","first-page":"3998","DOI":"10.1016\/j.asoc.2011.02.029","volume":"11","author":"PC Chang","year":"2011","unstructured":"Chang PC, Liao TW, Lin JJ, Fan CY (2011) A dynamic threshold decision system for stock trading signal detection. Appl Soft Comput 11(5):3998\u20134010","journal-title":"Appl Soft Comput"},{"key":"773_CR6","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.jpdc.2019.07.014","volume":"134","author":"V Chang","year":"2019","unstructured":"Chang V, Li T, Zeng Z (2019) Towards an improved adaboost algorithmic method for computational financial analysis. J Parallel Distrib Comput 134:219\u2013232","journal-title":"J Parallel Distrib Comput"},{"issue":"9","key":"773_CR7","doi-asserted-by":"publisher","first-page":"1610","DOI":"10.1016\/j.ins.2010.01.014","volume":"180","author":"CH Cheng","year":"2010","unstructured":"Cheng CH, Chen TL, Wei LY (2010) A hybrid model based on rough sets theory and genetic algorithms for stock price forecasting. Inf Sci 180(9):1610\u20131629","journal-title":"Inf Sci"},{"issue":"6","key":"773_CR8","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1016\/j.knosys.2010.04.007","volume":"23","author":"YWC Chien","year":"2010","unstructured":"Chien YWC, Chen YL (2010) Mining associative classification rules with stock trading data-a ga-based method. Knowl-Based Syst 23(6):605\u2013614","journal-title":"Knowl-Based Syst"},{"key":"773_CR9","unstructured":"Dulac-Arnold G, Evans R, van Hasselt H, Sunehag P, Lillicrap T, Hunt J, Mann T, Weber T, Degris T, Coppin B (2015) Deep reinforcement learning in large discrete action spaces. arXiv preprint arXiv:1512.07679"},{"key":"773_CR10","unstructured":"Foerster J, Assael IA, de\u00a0Freitas N, Whiteson S (2016) Learning to communicate with deep multi-agent reinforcement learning. In: Advances in neural information processing systems, pp 2137\u20132145"},{"key":"773_CR11","doi-asserted-by":"crossref","unstructured":"Foerster JN, Farquhar G, Afouras T, Nardelli N, Whiteson S (2018) Counterfactual multi-agent policy gradients. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11794"},{"issue":"8","key":"773_CR12","doi-asserted-by":"publisher","first-page":"10389","DOI":"10.1016\/j.eswa.2011.02.068","volume":"38","author":"E Guresen","year":"2011","unstructured":"Guresen E, Kayakutlu G, Daim TU (2011) Using artificial neural network models in stock market index prediction. Expert Syst Appl 38(8):10389\u201310397","journal-title":"Expert Syst Appl"},{"issue":"3","key":"773_CR13","doi-asserted-by":"publisher","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","volume":"2","author":"T Hastie","year":"2009","unstructured":"Hastie T, Rosset S, Zhu J, Zou H (2009) Multi-class adaboost. Stat Interface 2(3):349\u2013360","journal-title":"Stat Interface"},{"key":"773_CR14","unstructured":"jpmorgan. https:\/\/www.businessinsider.com\/jpmorgan-takes-ai-use-to-the-next-level-2017-8"},{"key":"773_CR15","doi-asserted-by":"crossref","unstructured":"Koutn\u00edk J, Schmidhuber J, Gomez F (2014) Online evolution of deep convolutional network for vision-based reinforcement learning. In: International conference on simulation of adaptive behavior, pp 260\u2013269. Springer","DOI":"10.1007\/978-3-319-08864-8_25"},{"key":"773_CR16","unstructured":"Krollner B, Vanstone BJ, Finnie GR (2010) Financial time series forecasting with machine learning techniques: a survey. ESANN 2010, 18th European Symposium on Artificial Neural Networks, Bruges, Belgium, April 28\u201330, 2010, Proceedings. https:\/\/www.elen.ucl.ac.be\/Proceedings\/esann\/esannpdf\/es2010-50.pdf"},{"key":"773_CR17","doi-asserted-by":"crossref","unstructured":"Lange S, Riedmiller M (2010) Deep auto-encoder neural networks in reinforcement learning. In: The 2010 international joint conference on neural networks (IJCNN), pp 1\u20138. IEEE","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"773_CR18","doi-asserted-by":"crossref","unstructured":"Lange S, Riedmiller M, Voigtlander A (2012) Autonomous reinforcement learning on raw visual input data in a real world application. In: The 2012 international joint conference on neural networks (IJCNN), pp 1\u20138. IEEE","DOI":"10.1109\/IJCNN.2012.6252823"},{"issue":"1","key":"773_CR19","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1016\/j.eswa.2009.05.086","volume":"37","author":"Z Liao","year":"2010","unstructured":"Liao Z, Wang J (2010) Forecasting model of global stock index by stochastic time effective neural network. Expert Syst Appl 37(1):834\u2013841","journal-title":"Expert Syst Appl"},{"key":"773_CR20","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"key":"773_CR21","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.asoc.2015.07.020","volume":"36","author":"S Mabu","year":"2015","unstructured":"Mabu S, Obayashi M, Kuremoto T (2015) Ensemble learning of rule-based evolutionary algorithm using multi-layer perceptron for supporting decisions in stock trading problems. Appl Soft Comput 36:357\u2013367","journal-title":"Appl Soft Comput"},{"key":"773_CR22","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602"},{"issue":"7540","key":"773_CR23","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529","journal-title":"Nature"},{"key":"773_CR24","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv preprint arXiv:1511.05952"},{"key":"773_CR25","unstructured":"Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: International conference on machine learning, pp 1889\u20131897"},{"key":"773_CR26","unstructured":"Shibata K, Iida M (2003) Acquisition of box pushing by direct-vision-based reinforcement learning. In: SICE 2003 annual conference, vol\u00a03, pp 2322\u20132327. IEEE"},{"key":"773_CR27","unstructured":"Shibata K, Okabe Y (1997) Reinforcement learning when visual sensory signals are directly given as inputs. In: International conference on neural networks, 1997. vol\u00a03, pp 1716\u20131720. IEEE"},{"key":"773_CR28","unstructured":"Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms. In: ICML"},{"key":"773_CR29","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: AAAI, vol\u00a02, p\u00a05. Phoenix, AZ","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"773_CR30","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.matcom.2011.01.002","volume":"86","author":"B Vanstone","year":"2012","unstructured":"Vanstone B, Finnie G, Hahn T (2012) Creating trading systems with fundamental variables and neural networks: the aby case study. Math Comput Simul 86:78\u201391","journal-title":"Math Comput Simul"},{"key":"773_CR31","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.asoc.2016.07.024","volume":"49","author":"J Wang","year":"2016","unstructured":"Wang J, Hou R, Wang C, Shen L (2016) Improved v-support vector regression model based on variable selection and brain storm optimization for stock price forecasting. Appl Soft Comput 49:164\u2013178","journal-title":"Appl Soft Comput"},{"issue":"11","key":"773_CR32","doi-asserted-by":"crossref","first-page":"14346","DOI":"10.1016\/j.eswa.2011.04.222","volume":"38","author":"JZ Wang","year":"2011","unstructured":"Wang JZ, Wang JJ, Zhang ZG, Guo SP (2011) Forecasting stock indices with back propagation neural network. Expert Syst Appl 38(11):14346\u201314355","journal-title":"Expert Syst Appl"},{"key":"773_CR33","unstructured":"Wang Z, Schaul T, Hessel M, Van\u00a0Hasselt H, Lanctot M, De\u00a0Freitas N (2015) Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581"},{"key":"773_CR34","unstructured":"Wymann B, Espi\u00e9 E, Guionneau C, Dimitrakakis C, Coulom R, Sumner A (2000) Torcs, the open racing car simulator. Software available at http:\/\/torcs.sourceforge.net. Accessed 3 July 2019"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-019-00773-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00607-019-00773-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-019-00773-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T06:38:57Z","timestamp":1665297537000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00607-019-00773-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,23]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["773"],"URL":"https:\/\/doi.org\/10.1007\/s00607-019-00773-w","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,23]]},"assertion":[{"value":"8 August 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}