{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T11:16:04Z","timestamp":1783163764048,"version":"3.54.6"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100015401","name":"Shaanxi Province Key Research and Development Projects","doi-asserted-by":"publisher","award":["2023GXLH-036"],"award-info":[{"award-number":["2023GXLH-036"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031935","name":"Xi'an Jiaotong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031935","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005311","name":"China Southern Power Grid Co Ltd","doi-asserted-by":"publisher","award":["CG2800022001651817-5"],"award-info":[{"award-number":["CG2800022001651817-5"]}],"id":[{"id":"10.13039\/501100005311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104452","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:08:08Z","timestamp":1778170088000},"page":"104452","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dancing with markets: A dynamic rebalancing mechanism using deep reinforcement learning for online portfolio selection"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2262-2743","authenticated-orcid":false,"given":"Qing","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7634-2018","authenticated-orcid":false,"given":"Chenyu","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1328-0331","authenticated-orcid":false,"given":"Shan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7649-0750","authenticated-orcid":false,"given":"Yuze","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104452_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.gfj.2024.101016","article-title":"Deep reinforcement learning for portfolio selection","volume":"62","author":"Jiang","year":"2024","journal-title":"Global Finance J."},{"key":"10.1016\/j.inffus.2026.104452_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102165","article-title":"Quantitative stock portfolio optimization by multi-task learning risk and return","volume":"104","author":"Ma","year":"2024","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.inffus.2026.104452_bib0003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.1467-9965.1991.tb00002.x","article-title":"Universal portfolios","volume":"1","author":"Cover","year":"1991","journal-title":"Math. Finance"},{"key":"10.1016\/j.inffus.2026.104452_bib0004","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s10994-012-5281-z","article-title":"PAMR: passive aggressive mean reversion strategy for portfolio selection","volume":"87","author":"Li","year":"2012","journal-title":"Mach. Learn."},{"key":"10.1016\/j.inffus.2026.104452_bib0005","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.artint.2015.01.006","article-title":"Moving average reversion strategy for on-line portfolio selection","volume":"222","author":"Li","year":"2015","journal-title":"Artif. Intell."},{"issue":"2","key":"10.1016\/j.inffus.2026.104452_bib0006","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1111\/j.1467-9965.2006.00274.x","article-title":"Nonparametric kernel-based sequential investment strategies","volume":"16","author":"Gy\u00f6rfi","year":"2006","journal-title":"Math. Finance"},{"issue":"3","key":"10.1016\/j.inffus.2026.104452_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103247","article-title":"Online portfolio management via deep reinforcement learning with high-frequency data","volume":"60","author":"Li","year":"2023","journal-title":"Inf. Process. Manag."},{"issue":"5","key":"10.1016\/j.inffus.2026.104452_bib0008","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3200692","article-title":"Combination forecasting reversion strategy for online portfolio selection","volume":"9","author":"Huang","year":"2018","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.inffus.2026.104452_bib0009","series-title":"2024 IEEE International Conference on Quantum Computing and Engineering (QCE)","first-page":"1516","article-title":"Differentiable quantum architecture search in asynchronous quantum reinforcement learning","volume":"01","author":"Chen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104452_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114002","article-title":"Deep reinforcement learning for portfolio management of markets with a dynamic number of assets","volume":"164","author":"Betancourt","year":"2021","journal-title":"Expert Syst. Appl."},{"issue":"5","key":"10.1016\/j.inffus.2026.104452_bib0011","doi-asserted-by":"crossref","first-page":"3117","DOI":"10.1007\/s10614-024-10555-y","article-title":"Constructing optimal portfolio rebalancing strategies with a two-stage multiresolution-grid model","volume":"64","author":"Dai","year":"2024","journal-title":"Comput. Econ."},{"key":"10.1016\/j.inffus.2026.104452_bib0012","series-title":"2019 Amity International Conference on Artificial Intelligence (AICAI)","first-page":"14","article-title":"Deep reinforcement learning for optimizing finance portfolio management","author":"Hu","year":"2019"},{"key":"10.1016\/j.inffus.2026.104452_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126430","article-title":"Optimizing portfolio selection through stock ranking and matching: a reinforcement learning approach","volume":"269","author":"Alzaman","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"10.1016\/j.inffus.2026.104452_bib0014","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.ejor.2024.08.027","article-title":"Integration of prediction and optimization for smart stock portfolio selection","volume":"321","author":"Sarkar","year":"2025","journal-title":"Eur. J. Oper. Res."},{"issue":"7","key":"10.1016\/j.inffus.2026.104452_bib0015","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1057\/jors.2016.21","article-title":"Developing a dynamic portfolio selection model with a self-adjusted rebalancing method","volume":"68","author":"Jung","year":"2017","journal-title":"J. Oper. Res. Soc."},{"key":"10.1016\/j.inffus.2026.104452_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.techfore.2023.122944","article-title":"Multi-period portfolio optimization using a deep reinforcement learning hyper-heuristic approach","volume":"198","author":"Cui","year":"2024","journal-title":"Technol. Forecast. Soc. Change"},{"issue":"4","key":"10.1016\/j.inffus.2026.104452_bib0017","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1002\/j.1538-7305.1956.tb03809.x","article-title":"A new interpretation of information rate","volume":"35","author":"Kelly","year":"1956","journal-title":"Bell Syst. Tech. J."},{"issue":"4","key":"10.1016\/j.inffus.2026.104452_bib0018","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1111\/1467-9965.00058","article-title":"On-line portfolio selection using multiplicative updates","volume":"8","author":"Helmbold","year":"1998","journal-title":"Math. Finance"},{"issue":"1","key":"10.1016\/j.inffus.2026.104452_bib0019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2435209.2435213","article-title":"Confidence weighted mean reversion strategy for online portfolio selection","volume":"7","author":"Li","year":"2013","journal-title":"ACM Trans. Knowl. Discov. Data"},{"issue":"3","key":"10.1016\/j.inffus.2026.104452_bib0020","first-page":"1","article-title":"Online portfolio selection: a survey","volume":"46","author":"Li","year":"2014","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.inffus.2026.104452_bib0021","series-title":"Advances in Neural Information Processing Systems","article-title":"Optimal asset allocation using adaptive dynamic programming","volume":"8","author":"Neuneier","year":"1995"},{"issue":"4","key":"10.1016\/j.inffus.2026.104452_bib0022","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":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.inffus.2026.104452_bib0023","unstructured":"Z. Jiang, D. Xu, J. Liang, A deep reinforcement learning framework for the financial portfolio management problem, 2017, https:\/\/arxiv.org\/abs\/1706.10059."},{"key":"10.1016\/j.inffus.2026.104452_bib0024","first-page":"1","article-title":"A novel approach for dynamic portfolio management integrating K-means clustering, mean-variance optimization, and reinforcement learning","author":"Zouaghia","year":"2025","journal-title":"Knowl. Inf. Syst."},{"key":"10.1016\/j.inffus.2026.104452_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.iref.2025.103996","article-title":"High-dimensional multi-period portfolio allocation using deep reinforcement learning","volume":"98","author":"Jiang","year":"2025","journal-title":"Int. Rev. Econ. Finance"},{"key":"10.1016\/j.inffus.2026.104452_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.ribaf.2025.102836","article-title":"The effects of portfolio rebalancing strategies on the performance of global mutual funds","volume":"76","author":"Tanos","year":"2025","journal-title":"Res. Int. Bus. Finance"},{"key":"10.1016\/j.inffus.2026.104452_bib0027","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.1787045","article-title":"Why does an equal-weighted portfolio outperform value-and price-weighted portfolios?","author":"Plyakha","year":"2012","journal-title":"SSRN Electron. J."},{"key":"10.1016\/j.inffus.2026.104452_bib0028","series-title":"Investment Science","author":"Luenberger","year":"1998"},{"key":"10.1016\/j.inffus.2026.104452_bib0029","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 Syst. Appl."},{"key":"10.1016\/j.inffus.2026.104452_bib0030","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.frl.2014.11.001","article-title":"Conditional sharpe ratios","volume":"12","author":"Chow","year":"2015","journal-title":"Finance Res. Lett."},{"issue":"9","key":"10.1016\/j.inffus.2026.104452_bib0031","doi-asserted-by":"crossref","first-page":"7125","DOI":"10.1007\/s00521-021-06853-3","article-title":"Dynamic portfolio rebalancing through reinforcement learning","volume":"34","author":"Lim","year":"2022","journal-title":"Neural Comput. Appl."},{"issue":"2","key":"10.1016\/j.inffus.2026.104452_bib0032","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1002\/fut.21977","article-title":"Settlement procedures and stock market efficiency","volume":"39","author":"Lin","year":"2019","journal-title":"J. Futures Mark."},{"issue":"3","key":"10.1016\/j.inffus.2026.104452_bib0033","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1086\/260062","article-title":"The pricing of options and corporate liabilities","volume":"81","author":"Black","year":"1973","journal-title":"J. Polit. Econ."},{"issue":"8","key":"10.1016\/j.inffus.2026.104452_bib0034","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1080\/14697688.2017.1357831","article-title":"Transaction cost optimization for online portfolio selection","volume":"18","author":"Li","year":"2018","journal-title":"Quant. Finance"},{"issue":"3","key":"10.1016\/j.inffus.2026.104452_bib0035","doi-asserted-by":"crossref","DOI":"10.1145\/1961189.1961193","article-title":"CORN: correlation-driven nonparametric learning approach for portfolio selection","volume":"2","author":"Li","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"1","key":"10.1016\/j.inffus.2026.104452_bib0036","doi-asserted-by":"crossref","DOI":"10.1145\/2435209.2435213","article-title":"Confidence weighted mean reversion strategy for online portfolio selection","volume":"7","author":"Li","year":"2013","journal-title":"ACM Trans. Knowl. Discov. Data"},{"issue":"6","key":"10.1016\/j.inffus.2026.104452_bib0037","doi-asserted-by":"crossref","first-page":"2405","DOI":"10.1007\/s10614-023-10411-5","article-title":"Weak aggregating specialist algorithm for online portfolio selection","volume":"63","author":"He","year":"2024","journal-title":"Comput. Econ."},{"issue":"8","key":"10.1016\/j.inffus.2026.104452_bib0038","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1080\/01605682.2022.2122737","article-title":"Aggregating exponential gradient expert advice for online portfolio selection under transaction costs","volume":"74","author":"Zhang","year":"2023","journal-title":"J. Oper. Res. Soc."},{"key":"10.1016\/j.inffus.2026.104452_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.econmod.2022.106078","article-title":"Portfolio constructions in cryptocurrency market: a CVaR-based deep reinforcement learning approach","volume":"119","author":"Cui","year":"2023","journal-title":"Econ. Model."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003325?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003325?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T10:22:40Z","timestamp":1783160560000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":39,"alternative-id":["S1566253526003325"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104452","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dancing with markets: A dynamic rebalancing mechanism using deep reinforcement learning for online portfolio selection","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104452","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104452"}}