{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T08:39:26Z","timestamp":1774255166559,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"name":"RIE2025 Industry Alignment Fund – Industry Collaboration Projects (IAF-ICP)","award":["I2301E0026"],"award-info":[{"award-number":["I2301E0026"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,22]]},"DOI":"10.1145\/3773966.3777972","type":"proceedings-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:50:01Z","timestamp":1771264201000},"page":"1017-1026","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["STORM: A Spatio-Temporal Factor Model Based on Dual Vector Quantized Variational Autoencoders for Financial Trading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4226-1456","authenticated-orcid":false,"given":"Yilei","family":"Zhao","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2767-6998","authenticated-orcid":false,"given":"Wentao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3890-7713","authenticated-orcid":false,"given":"Tingran","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4482-1559","authenticated-orcid":false,"given":"Yong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-5053","authenticated-orcid":false,"given":"Fei","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2150-5561","authenticated-orcid":false,"given":"Wei Yang Bryan","family":"Lim","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, Vol. 33 (2020), 12449-12460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the IEEE\/CVF international Conference on Computer Vision. 357-366","author":"Richard Chen Chun-Fu","year":"2021","unstructured":"Chun-Fu Richard Chen, Quanfu Fan, and Rameswar Panda. 2021. Crossvit: Cross-attention multi-scale vision transformer for image classification. In Proceedings of the IEEE\/CVF international Conference on Computer Vision. 357-366."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","first-page":"530","DOI":"10.18293\/SEKE2023-168","article-title":"mTrader: A Multi-Scale Signal Optimization Deep Reinforcement Learning Framework for Financial Trading (S)","author":"Chen Zhennan","year":"2023","unstructured":"Zhennan Chen, Zhicheng Zhang, Pengfei Li, Lingyue Wei, Shibo Feng, and Fan Lin. 2023. mTrader: A Multi-Scale Signal Optimization Deep Reinforcement Learning Framework for Financial Trading (S).. In SEKE. 530-535.","journal-title":"SEKE."},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning (ICML).","author":"Dao Tri","year":"2024","unstructured":"Tri Dao and Albert Gu. 2024. Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_5_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20369"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1992.tb04398.x"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16083"},{"key":"e_1_3_2_1_9_1","volume-title":"The little book that still beats the market","author":"Greenblatt Joel","unstructured":"Joel Greenblatt. 2010. The little book that still beats the market. Vol. 29. John Wiley & Sons."},{"key":"e_1_3_2_1_10_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2020.07.009"},{"key":"e_1_3_2_1_12_1","unstructured":"Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel et al. 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541315"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International Conference on Machine Learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5587"},{"key":"e_1_3_2_1_18_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_19_1","volume-title":"A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730","author":"Nie Yuqi","year":"2022","unstructured":"Yuqi Nie, Nam H Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2022. A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730 (2022)."},{"key":"e_1_3_2_1_20_1","first-page":"27","article-title":"Mean reversion in stock prices: Evidence and implications","volume":"22","author":"Poterba James M","year":"1988","unstructured":"James M Poterba and Lawrence H Summers. 1988. Mean reversion in stock prices: Evidence and implications. Journal of Jinancial Economics, Vol. 22, 1 (1988), 27-59.","journal-title":"Journal of Jinancial Economics"},{"key":"e_1_3_2_1_21_1","volume-title":"A dual-stage attention-based recurrent neural network for time series prediction. arXiv preprint arXiv:1704.02971","author":"Qin Yao","year":"2017","unstructured":"Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, and Garrison Cottrell. 2017. A dual-stage attention-based recurrent neural network for time series prediction. arXiv preprint arXiv:1704.02971 (2017)."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_23_1","volume-title":"Aaron Van den Oord, and Oriol Vinyals","author":"Razavi Ali","year":"2019","unstructured":"Ali Razavi, Aaron Van den Oord, and Oriol Vinyals. 2019. Generating diverse high-fidelity images with vq-vae-2. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0531(76)90046-6"},{"key":"e_1_3_2_1_25_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_26_1","first-page":"425","article-title":"Capital asset prices: A theory of market equilibrium under conditions of risk","volume":"19","author":"Sharpe William F","year":"1964","unstructured":"William F Sharpe. 1964. Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance, Vol. 19, 3 (1964), 425-442.","journal-title":"The Journal of Finance"},{"key":"e_1_3_2_1_27_1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5.","author":"Shin Woncheol","year":"2023","unstructured":"Woncheol Shin, Gyubok Lee, Jiyoung Lee, Eunyi Lyou, Joonseok Lee, and Edward Choi. 2023. Exploration into translation-equivariant image quantization. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5."},{"key":"e_1_3_2_1_28_1","volume-title":"Robust market making via adversarial reinforcement learning. arXiv preprint arXiv:2003.01820","author":"Spooner Thomas","year":"2020","unstructured":"Thomas Spooner and Rahul Savani. 2020. Robust market making via adversarial reinforcement learning. arXiv preprint arXiv:2003.01820 (2020)."},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Sun Shuo","year":"2024","unstructured":"Shuo Sun, Molei Qin, Wentao Zhang, Haochong Xia, Chuqiao Zong, Jie Ying, Yonggang Xie, Lingxuan Zhao, Xinrun Wang, and Bo An. 2024. TradeMaster: a holistic quantitative trading platform empowered by reinforcement learning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557283"},{"key":"e_1_3_2_1_31_1","volume-title":"TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis. arXiv preprint arXiv:2402.16412","author":"Talukder Sabera","year":"2024","unstructured":"Sabera Talukder, Yisong Yue, and Georgia Gkioxari. 2024. TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis. arXiv preprint arXiv:2402.16412 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Den Oord Aaron Van","year":"2017","unstructured":"Aaron Van Den Oord, Oriol Vinyals, et al., 2017. Neural discrete representation learning. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_34_1","volume-title":"CLVSA: A convolutional LSTM based variational sequence-to-sequence model with attention for predicting trends of financial markets. arXiv preprint arXiv:2104.04041","author":"Wang Jia","year":"2021","unstructured":"Jia Wang, Tong Sun, Benyuan Liu, Yu Cao, and Hongwei Zhu. 2021b. CLVSA: A convolutional LSTM based variational sequence-to-sequence model with attention for predicting trends of financial markets. arXiv preprint arXiv:2104.04041 (2021)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16144"},{"key":"e_1_3_2_1_36_1","volume-title":"Factor investing with a deep multi-factor model. arXiv preprint arXiv:2210.12462","author":"Wei Zikai","year":"2022","unstructured":"Zikai Wei, Bo Dai, and Dahua Lin. 2022. Factor investing with a deep multi-factor model. arXiv preprint arXiv:2210.12462 (2022)."},{"key":"e_1_3_2_1_37_1","volume-title":"HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE. arXiv preprint arXiv:2306.02848","author":"Wei Zikai","year":"2023","unstructured":"Zikai Wei, Anyi Rao, Bo Dai, and Dahua Lin. 2023. HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE. arXiv preprint arXiv:2306.02848 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157","author":"Yan Wilson","year":"2021","unstructured":"Wilson Yan, Yunzhi Zhang, Pieter Abbeel, and Aravind Srinivas. 2021. Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157 (2021)."},{"key":"e_1_3_2_1_39_1","volume-title":"Qlib: An ai-oriented quantitative investment platform. arXiv preprint arXiv:2009.11189","author":"Yang Xiao","year":"2020","unstructured":"Xiao Yang, Weiqing Liu, Dong Zhou, Jiang Bian, and Tie-Yan Liu. 2020. Qlib: An ai-oriented quantitative investment platform. arXiv preprint arXiv:2009.11189 (2020)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5462"},{"key":"e_1_3_2_1_41_1","volume-title":"Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu and Vladlen Koltun. 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015), 1-10."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-72745-5_29"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7757-7766","author":"Zhang Baoquan","year":"2024","unstructured":"Baoquan Zhang, Huaibin Wang, Chuyao Luo, Xutao Li, Guotao Liang, Yunming Ye, Xiaochen Qi, and Yao He. 2024a. Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7757-7766."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Wentao Zhang Lingxuan Zhao Haochong Xia Shuo Sun Jiaze Sun Molei Qin Xinyi Li Yuqing Zhao Yilei Zhao Xinyu Cai et al. 2024c. FinAgent: A Multimodal Foundation Agent for Financial Trading: Tool-Augmented Diversified and Generalist. arXiv preprint arXiv:2402.18485 (2024).","DOI":"10.1145\/3637528.3671801"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645615"},{"key":"e_1_3_2_1_46_1","first-page":"8559","article-title":"Stock movement prediction based on bi-typed hybrid-relational market knowledge graph via dual attention networks","volume":"35","author":"Zhao Yu","year":"2022","unstructured":"Yu Zhao, Huaming Du, Ying Liu, Shaopeng Wei, Xingyan Chen, Fuzhen Zhuang, Qing Li, and Gang Kou. 2022. Stock movement prediction based on bi-typed hybrid-relational market knowledge graph via dual attention networks. IEEE Transactions on Knowledge and Data Engineering, Vol. 35, 8 (2022), 8559-8571.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"}],"event":{"name":"WSDM '26:The Nineteenth ACM International Conference on Web Search and Data Mining","location":"Boise ID USA","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:59:45Z","timestamp":1771264785000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773966.3777972"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":46,"alternative-id":["10.1145\/3773966.3777972","10.1145\/3773966"],"URL":"https:\/\/doi.org\/10.1145\/3773966.3777972","relation":{},"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"2026-02-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}