{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:44:14Z","timestamp":1777409054612,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,14]]},"DOI":"10.1145\/3677052.3698684","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:38:06Z","timestamp":1731566286000},"page":"822-830","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Transformers and attention-based networks in quantitative trading: a comprehensive survey"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6499-912X","authenticated-orcid":false,"given":"Lucas","family":"Coelho e Silva","sequence":"first","affiliation":[{"name":"Aeronautics Institute of Technology, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6802-6897","authenticated-orcid":false,"given":"Gustavo de Freitas","family":"Fonseca","sequence":"additional","affiliation":[{"name":"Aeronautics Institute of Technology, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5515-1672","authenticated-orcid":false,"given":"Paulo Andre L.","family":"Castro","sequence":"additional","affiliation":[{"name":"Aeronautics Institute of Technology, Brazil"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2023.2286351"},{"key":"e_1_3_2_1_2_1","unstructured":"Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural Machine Translation by Jointly Learning to Align and Translate. http:\/\/arxiv.org\/abs\/1409.0473 arXiv:1409.0473 [cs stat]."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Fazl Barez Paul Bilokon Arthur Gervais and Nikita Lisitsyn. 2023. Exploring the Advantages of Transformers for High-Frequency Trading. http:\/\/arxiv.org\/abs\/2302.13850 arXiv:2302.13850 [cs q-fin].","DOI":"10.2139\/ssrn.4364833"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2013.00048"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Paul Bilokon and Yitao Qiu. 2023. Transformers versus LSTMs for electronic trading. http:\/\/arxiv.org\/abs\/2309.11400 arXiv:2309.11400 [cs econ q-fin].","DOI":"10.2139\/ssrn.4577922"},{"key":"e_1_3_2_1_6_1","unstructured":"Tom\u00a0B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel\u00a0M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. http:\/\/arxiv.org\/abs\/2005.14165 arXiv:2005.14165 [cs]."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Hieu\u00a0K. Cao Han\u00a0K. Cao and Binh\u00a0T. Nguyen. 2020. DELAFO: An Efficient Portfolio Optimization Using Deep Neural Networks. In Advances in Knowledge Discovery and Data Mining Hady\u00a0W. Lauw Raymond Chi-Wing Wong Alexandros Ntoulas Ee-Peng Lim See-Kiong Ng and Sinno\u00a0Jialin Pan (Eds.). Vol.\u00a012084. Springer International Publishing Cham 623\u2013635. https:\/\/doi.org\/10.1007\/978-3-030-47426-3_48 Series Title: Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-47426-3_48"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3212767"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_10_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. http:\/\/arxiv.org\/abs\/1810.04805 arXiv:1810.04805 [cs]."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123538"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13317"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191123"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eneco.2023.107106"},{"key":"e_1_3_2_1_16_1","volume-title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","author":"Jaegle Andrew","year":"2022","unstructured":"Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier H\u00e9naff, Matthew\u00a0M. Botvinick, Andrew Zisserman, Oriol Vinyals, and Jo\u0101o Carreira. 2022. Perceiver IO: A General Architecture for Structured Inputs & Outputs. http:\/\/arxiv.org\/abs\/2107.14795 arXiv:2107.14795 [cs, eess]."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003170082"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2701\/1\/012134"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3236032"},{"key":"e_1_3_2_1_20_1","volume-title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition. Advances in Neural Information Processing Systems 35 (Dec.","author":"Kim Sehoon","year":"2022","unstructured":"Sehoon Kim, Amir Gholami, Albert Shaw, Nicholas Lee, Karttikeya Mangalam, Jitendra Malik, Michael\u00a0W. Mahoney, and Kurt Keutzer. 2022. Squeezeformer: An Efficient Transformer for Automatic Speech Recognition. Advances in Neural Information Processing Systems 35 (Dec. 2022), 9361\u20139373. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/3ccf6da39eeb8fefc8bbb1b0124adbd1-Abstract-Conference.html"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2023.2294799"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSDE50874.2020.9411635"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2001.04451"},{"key":"e_1_3_2_1_24_1","unstructured":"Junghwan Lee Chen Xu and Yao Xie. 2024. Transformer Conformal Prediction for Time Series. http:\/\/arxiv.org\/abs\/2406.05332 arXiv:2406.05332 [cs]."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7739087"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626869"},{"key":"e_1_3_2_1_27_1","unstructured":"Yuanzhe Li Yue Wu and Peng Yang. 2024. SimLOB: Learning Representations of Limited Order Book for Financial Market Simulation. http:\/\/arxiv.org\/abs\/2406.19396 arXiv:2406.19396 [cs]."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488378"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3227717"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Alejandro Lopez-Lira and Yuehua Tang. 2023. Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models. http:\/\/arxiv.org\/abs\/2304.07619 arXiv:2304.07619 [cs q-fin].","DOI":"10.2139\/ssrn.4412788"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06568-1"},{"key":"e_1_3_2_1_33_1","volume-title":"Inside the black box: a simple guide to quantitative and high-frequency trading","author":"Narang K.","unstructured":"Rishi\u00a0K. Narang. 2013. Inside the black box: a simple guide to quantitative and high-frequency trading (second edition ed.). John Wiley & Sons, Inc, Hoboken, New Jersey."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.14730"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-024-00851-2"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfds.2024.100129"},{"key":"e_1_3_2_1_37_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving Language Understanding by Generative Pre-Training. https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/math9151794"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/IIAI-AAI-Winter58034.2022.00029"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-023-10470-8"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1108\/CFRI-01-2024-0032"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892317"},{"key":"e_1_3_2_1_43_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc\u00a0V. Le. 2014. Sequence to Sequence Learning with Neural Networks. http:\/\/arxiv.org\/abs\/1409.3215 arXiv:1409.3215 [cs]."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626841"},{"key":"e_1_3_2_1_45_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. http:\/\/arxiv.org\/abs\/2302.13971 arXiv:2302.13971 [cs]."},{"key":"e_1_3_2_1_46_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a030. Curran Associates","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141\u00a0ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, Vol.\u00a030. Curran Associates, Inc., Long Beach, CA, USA, 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_48_1","unstructured":"Kieran Wood Sven Giegerich Stephen Roberts and Stefan Zohren. 2022. Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture. http:\/\/arxiv.org\/abs\/2112.08534 arXiv:2112.08534 [cs q-fin stat]."},{"key":"e_1_3_2_1_49_1","unstructured":"Haixu Wu Jiehui Xu Jianmin Wang and Mingsheng Long. 2021. Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting. In Advances in Neural Information Processing Systems M.\u00a0Ranzato A.\u00a0Beygelzimer Y.\u00a0Dauphin P.\u00a0S. Liang and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates Inc. Online 22419\u201322430. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/bcc0d400288793e8bdcd7c19a8ac0c2b-Paper.pdf"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110211"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_3_2_1_52_1","unstructured":"Haohan Zhang Fengrui Hua Chengjin Xu Hao Kong Ruiting Zuo and Jian Guo. 2024. Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?http:\/\/arxiv.org\/abs\/2306.14222 arXiv:2306.14222 [cs q-fin]."},{"key":"e_1_3_2_1_53_1","unstructured":"Zhaofeng Zhang Banghao Chen Shengxin Zhu and Nicolas Langren\u00e9. 2024. From attention to profit: quantitative trading strategy based on transformer. http:\/\/arxiv.org\/abs\/2404.00424 arXiv:2404.00424 [cs q-fin]."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_55_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162)","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 Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162), Kamalika Chaudhuri, Stefanie Jegelka, Le\u00a0Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, Online, 27268\u201327286. https:\/\/proceedings.mlr.press\/v162\/zhou22g.html"}],"event":{"name":"ICAIF '24: 5th ACM International Conference on AI in Finance","location":"Brooklyn NY USA","acronym":"ICAIF '24"},"container-title":["Proceedings of the 5th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698684","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677052.3698684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:09:52Z","timestamp":1755882592000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":55,"alternative-id":["10.1145\/3677052.3698684","10.1145\/3677052"],"URL":"https:\/\/doi.org\/10.1145\/3677052.3698684","relation":{},"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}