{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:36:43Z","timestamp":1763105803492,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770411","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"788-796","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Long-Term Financial Forecasting and Trading via Multi-Agent Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2852-6205","authenticated-orcid":false,"given":"Yu","family":"Bi","sequence":"first","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9070-5252","authenticated-orcid":false,"given":"Zhuohan","family":"Wang","sequence":"additional","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5190-5365","authenticated-orcid":false,"given":"Lingxiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1464-1215","authenticated-orcid":false,"given":"Carmine","family":"Ventre","sequence":"additional","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28991"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Salvatore Carta Anselmo Ferreira Alessandro\u00a0Sebastian Podda Diego\u00a0Reforgiato Recupero and Antonio Sanna. 2021. Multi-DQN: An ensemble of Deep Q-learning agents for stock market forecasting. Expert systems with applications 164 (2021) 113820.","DOI":"10.1016\/j.eswa.2020.113820"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7364089"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/640"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1148"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20618"},{"key":"e_1_3_3_1_8_2","unstructured":"Scott Fujimoto and Shixiang\u00a0Shane Gu. 2021. A minimalist approach to offline reinforcement learning. Advances in neural information processing systems 34 (2021) 20132\u201320145."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Yuling Huang Chujin Zhou Kai Cui and Xiaoping Lu. 2024. A multi-agent reinforcement learning framework for optimizing financial trading strategies based on TimesNet. Expert Systems with Applications 237 (2024) 121502.","DOI":"10.1016\/j.eswa.2023.121502"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422570"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614844"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Namyeong Lee and Jun Moon. 2023. Offline reinforcement learning for automated stock trading. IEEE Access 11 (2023) 112577\u2013112589.","DOI":"10.1109\/ACCESS.2023.3324458"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Ziyue Li Shiwei Lyu Haipeng Zhang and Tianpei Jiang. 2021. One step ahead: a framework for detecting unexpected incidents and predicting the stock markets. IEEE Access 9 (2021) 30292\u201330305.","DOI":"10.1109\/ACCESS.2021.3059283"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1109\/IJCNN.2005.1555956","volume-title":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"2","author":"Liu Feng","year":"2005","unstructured":"Feng Liu, Chai Quek, and Geok\u00a0See Ng. 2005. Neural network model for time series prediction by reinforcement learning. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. , Vol.\u00a02. IEEE, 809\u2013814."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Guang Liu and Xiaojie Wang. 2018. A numerical-based attention method for stock market prediction with dual information. Ieee Access 7 (2018) 7357\u20137367.","DOI":"10.1109\/ACCESS.2018.2886367"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494366"},{"key":"e_1_3_3_1_17_2","unstructured":"Yong Liu Tengge Hu Haoran Zhang Haixu Wu Shiyu Wang Lintao Ma and Mingsheng Long. 2023. itransformer: Inverted transformers are effective for time series forecasting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.06625 (2023)."},{"key":"e_1_3_3_1_18_2","unstructured":"Yong Liu Haixu Wu Jianmin Wang and Mingsheng Long. 2022. Non-stationary transformers: Exploring the stationarity in time series forecasting. Advances in neural information processing systems 35 (2022) 9881\u20139893."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Johann Lussange Ivan Lazarevich Sacha Bourgeois-Gironde Stefano Palminteri and Boris Gutkin. 2021. Modelling stock markets by multi-agent reinforcement learning. Computational Economics 57 1 (2021) 113\u2013147.","DOI":"10.1007\/s10614-020-10038-w"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422524"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698639"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Abdul\u00a0Quadir Md Sanjit Kapoor Chris\u00a0Junni AV Arun\u00a0Kumar Sivaraman Kong\u00a0Fah Tee H Sabireen and N Janakiraman. 2023. Novel optimization approach for stock price forecasting using multi-layered sequential LSTM. Applied Soft Computing 134 (2023) 109830.","DOI":"10.1016\/j.asoc.2022.109830"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Latrisha\u00a0N Mintarya Jeta\u00a0NM Halim Callista Angie Said Achmad and Aditya Kurniawan. 2023. Machine learning approaches in stock market prediction: A systematic literature review. Procedia Computer Science 216 (2023) 96\u2013102.","DOI":"10.1016\/j.procs.2022.12.115"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Subba\u00a0Rao Polamuri Kudipudi Srinivas and A\u00a0Krishna Mohan. 2022. Multi-model generative adversarial network hybrid prediction algorithm (MMGAN-HPA) for stock market prices prediction. Journal of King Saud University-Computer and Information Sciences 34 9 (2022) 7433\u20137444.","DOI":"10.1016\/j.jksuci.2021.07.001"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Omer\u00a0Berat Sezer Mehmet\u00a0Ugur Gudelek and Ahmet\u00a0Murat Ozbayoglu. 2020. Financial time series forecasting with deep learning: A systematic literature review: 2005\u20132019. Applied soft computing 90 (2020) 106181.","DOI":"10.1016\/j.asoc.2020.106181"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Jaimin Shah Darsh Vaidya and Manan Shah. 2022. A comprehensive review on multiple hybrid deep learning approaches for stock prediction. Intelligent Systems with Applications 16 (2022) 200111.","DOI":"10.1016\/j.iswa.2022.200111"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Thanveer Shaik Xiaohui Tao Haoran Xie Lin Li Jianming Yong and Yuefeng Li. 2024. Graph-enabled reinforcement learning for time series forecasting with adaptive intelligence. IEEE Transactions on Emerging Topics in Computational Intelligence (2024).","DOI":"10.1109\/TETCI.2024.3398024"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Ali Shavandi and Majid Khedmati. 2022. A multi-agent deep reinforcement learning framework for algorithmic trading in financial markets. Expert Systems with Applications 208 (2022) 118124.","DOI":"10.1016\/j.eswa.2022.118124"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Wangwei Shu and Qiang Gao. 2020. Forecasting stock price based on frequency components by EMD and neural networks. Ieee Access 8 (2020) 206388\u2013206395.","DOI":"10.1109\/ACCESS.2020.3037681"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/I2CT54291.2022.9825415"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Yajiao Tang Zhenyu Song Yulin Zhu Huaiyu Yuan Maozhang Hou Junkai Ji Cheng Tang and Jianqiang Li. 2022. A survey on machine learning models for financial time series forecasting. Neurocomputing 512 (2022) 363\u2013380.","DOI":"10.1016\/j.neucom.2022.09.003"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533271.3561738"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Yuxuan Wang Haixu Wu Jiaxiang Dong Guo Qin Haoran Zhang Yong Liu Yunzhong Qiu Jianmin Wang and Mingsheng Long. 2024. Timexer: Empowering transformers for time series forecasting with exogenous variables. Advances in Neural Information Processing Systems 37 (2024) 469\u2013498.","DOI":"10.52202\/079017-0015"},{"key":"e_1_3_3_1_34_2","unstructured":"Muning Wen Jakub Kuba Runji Lin Weinan Zhang Ying Wen Jun Wang and Yaodong Yang. 2022. Multi-agent reinforcement learning is a sequence modeling problem. Advances in Neural Information Processing Systems 35 (2022) 16509\u201316521."},{"key":"e_1_3_3_1_35_2","unstructured":"Haixu Wu Tengge Hu Yong Liu Hang Zhou Jianmin Wang and Mingsheng Long. 2022. Timesnet: Temporal 2d-variation modeling for general time series analysis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.02186 (2022)."},{"key":"e_1_3_3_1_36_2","unstructured":"Haixu Wu Jiehui Xu Jianmin Wang and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in neural information processing systems 34 (2021) 22419\u201322430."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21414"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494398"},{"key":"e_1_3_3_1_39_2","first-page":"27268","volume-title":"International conference on machine learning","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International conference on machine learning. PMLR, 27268\u201327286."}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:27:18Z","timestamp":1763105238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":38,"alternative-id":["10.1145\/3768292.3770411","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770411","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}