{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T10:35:09Z","timestamp":1784284509949,"version":"3.55.0"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Social Science Foundation in Sichuan","award":["SC20TJ022"],"award-info":[{"award-number":["SC20TJ022"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2021YJG050"],"award-info":[{"award-number":["2021YJG050"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2022,8,31]]},"abstract":"<jats:p>\n            Although machine learning (ML) algorithms have been widely used in forecasting the trend of stock market indices, they failed to consider the following crucial aspects for market forecasting: (1) that investors\u2019 emotions and attitudes toward future market trends have material impacts on market trend forecasting (2) the length of past market data should be dynamically adjusted according to the market status and (3) the transition of market statutes should be considered when forecasting market trends. In this study, we proposed an innovative ML method to forecast China's stock market trends by addressing the three issues above. Specifically, sentimental factors (see Appendix [1] for full trans) were first collected to measure investors\u2019 emotions and attitudes. Then, a non-stationary Markov chain (NMC) model was used to capture dynamic transitions of market statutes. We choose the state-of-the-art (SOTA) method, namely, Bidirectional Encoder Representations from Transformers (\n            <jats:italic>BERT<\/jats:italic>\n            ), to predict the state of the market at time\n            <jats:italic>t<\/jats:italic>\n            , and a long short-term memory (\n            <jats:italic>LSTM<\/jats:italic>\n            ) model was used to estimate the varying length of past market data in market trend prediction, where the input of\n            <jats:italic>LSTM<\/jats:italic>\n            (the state of the market at time\n            <jats:italic>t<\/jats:italic>\n            ) was the output of\n            <jats:italic>BERT<\/jats:italic>\n            and probabilities for opening and closing of the gates in the\n            <jats:italic>LSTM<\/jats:italic>\n            model were based on outputs of the\n            <jats:italic>NMC<\/jats:italic>\n            model. Finally, the optimum parameters of the proposed algorithm were calculated using a reinforced learning-based deep Q-Network. Compared to existing forecasting methods, the proposed algorithm achieves better results with a forecasting accuracy of 61.77%, annualized return of 29.25%, and maximum losses of \u22128.29%. Furthermore, the proposed model achieved the lowest forecasting error: mean square error (0.095), root mean square error (0.0739), mean absolute error (0.104), and mean absolute percent error (15.1%). As a result, the proposed market forecasting model can help investors obtain more accurate market forecast information.\n          <\/jats:p>","DOI":"10.1145\/3488378","type":"journal-article","created":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T20:51:00Z","timestamp":1641675060000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Forecasting the Market with Machine Learning Algorithms: An Application of NMC-BERT-LSTM-DQN-X Algorithm in Quantitative Trading"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9790-9883","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"Southwestern University of Finance and Economics, Chengdu, Sichuan Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yan","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economics, Chengdu, Sichuan Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyue","family":"Guo","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economics, Chengdu, Sichuan Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Guo","sequence":"additional","affiliation":[{"name":"China Great-Wall Asset Management Co., Ltd, Chengdu, Sichuan Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,1,8]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-013-1386-y"},{"issue":"1","key":"e_1_3_2_3_1","first-page":"1","article-title":"Enhancing profit from stock transactions using neural networks","volume":"33","author":"Ahana R. C.","year":"2020","unstructured":"R. C. Ahana, A. Soheila, T. Michael, and K. Piyush. 2020. Enhancing profit from stock transactions using neural networks. AI Commun. 33, 1 (2020), 1\u201312.","journal-title":"AI Commun"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-4181(01)00024-6"},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.irfa.2014.07.013"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2012.05.003"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/jofi.12021"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.finmar.2003.11.005"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.21.2.129"},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/hhm030"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/07350015.2015.1037882"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2008.01373.x"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/rof\/rfx022"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.03.017"},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jempfin.2013.04.001"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2013.869698"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37429-7_7"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2794389"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.22105"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.14311\/NNW.2018.28.003"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2009.01493.x"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2013.12.002"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/fut.21867"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/15427560.2019.1588275"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.02.068"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1257\/aer.103.2.732"},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1017-z"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.02.055"},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2009.01483.x"},{"key":"e_1_3_2_30_1","unstructured":"Archives of Computational Methods in Engineering"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02101-8"},{"key":"e_1_3_2_32_1","unstructured":"Daiki Matsunaga Toyotaro Suzumura and Toshihiro Takahashi. 2019. Exploring graph neural networks for stock market predictions with rolling window analysis. Retrieved November 1 2021 from https:\/\/arxiv.org\/abs\/1909.10660."},{"issue":"10","key":"e_1_3_2_33_1","first-page":"4663","article-title":"Applying Bert to analyze investor sentiment in stock market","volume":"33","author":"Menggang L.","year":"2020","unstructured":"L. Menggang, L. Wenrui, F. Wang, X. Jia, and G. Rui. 2020. Applying Bert to analyze investor sentiment in stock market. Neural Computing and Applications 33, 10 (2020), 4663\u20134676. DOI:http:\/\/dx.doi.org\/10.1007\/s00521-020-05411-7","journal-title":"Neural Computing and Applications"},{"key":"e_1_3_2_34_1","volume-title":"ECML PKDD 2018 Workshops","author":"Nakagawa K.","year":"2019","unstructured":"K. Nakagawa, T. Uchida, and T. Aoshima. 2019. Deep factor model. In ECML PKDD 2018 Workshops. Springer, Cham."},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.07.052"},{"key":"e_1_3_2_36_1","unstructured":"R. Nyman and P. Ormerod. 2014. Big data socio-psychological theory algorithmic text analysis and predicting the Michigan consumer sentiment index. Retrieved November 1 2021 from https:\/\/arxiv.org\/abs\/1405.5695."},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.040"},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.10.031"},{"key":"e_1_3_2_39_1","unstructured":"Prozil Pinto and Ana Filipa. 2018. A principal component approach to measure investor sentiment and its impact on ipo's underpricing. Retrieved from https:\/\/repositorio-aberto.up.pt\/bitstream\/10216\/116313\/2\/294407.pdf."},{"key":"e_1_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2005.04.005"},{"key":"e_1_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327757.3327876"},{"key":"e_1_3_2_42_1","volume-title":"Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS\u201917)","author":"Wen Ruofeng","year":"2017","unstructured":"Ruofeng Wen, Kari Torkkola, Balakrishnan Narayanaswamy, and Dhruv Madeka. 2017. A multi-horizon quantile recurrent forecaster. In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS\u201917)."},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.095"},{"key":"e_1_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.04.013"},{"key":"e_1_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2006.10.002"},{"key":"e_1_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.02.041"},{"key":"e_1_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.06.016"},{"key":"e_1_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.frl.2018.02.009"},{"key":"e_1_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.22225"},{"key":"e_1_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/INMIC.2005.334420"},{"key":"e_1_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1351-7"},{"key":"e_1_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.12.035"},{"key":"e_1_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.5539\/emr.v1n2p46"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488378","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:24Z","timestamp":1750188624000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,8]]},"references-count":52,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8,31]]}},"alternative-id":["10.1145\/3488378"],"URL":"https:\/\/doi.org\/10.1145\/3488378","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,8]]},"assertion":[{"value":"2020-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}