{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/temporal-attention-augmented-bilinear-network","title":"Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis","arxiv_id":"1712.00975","date":"2017-12-04","proceeding":null,"authors":["Dat Thanh Tran","Alexandros Iosifidis","Juho Kanniainen","Moncef Gabbouj"],"abstract":"Financial time-series forecasting has long been a challenging problem because\nof the inherently noisy and stochastic nature of the market. In the\nHigh-Frequency Trading (HFT), forecasting for trading purposes is even a more\nchallenging task since an automated inference system is required to be both\naccurate and fast. In this paper, we propose a neural network layer\narchitecture that incorporates the idea of bilinear projection as well as an\nattention mechanism that enables the layer to detect and focus on crucial\ntemporal information. The resulting network is highly interpretable, given its\nability to highlight the importance and contribution of each temporal instance,\nthus allowing further analysis on the time instances of interest. Our\nexperiments in a large-scale Limit Order Book (LOB) dataset show that a\ntwo-hidden-layer network utilizing our proposed layer outperforms by a large\nmargin all existing state-of-the-art results coming from much deeper\narchitectures while requiring far fewer computations.","url_abs":"http://arxiv.org/abs/1712.00975v1","url_pdf":"http://arxiv.org/pdf/1712.00975v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"temporal-attention-augmented-bilinear-network","repo_url":"https://github.com/LeonardoBerti07/TABL-Temporal-Attention-Augmented-Bilinear-Network-for-Financial-Time-Series-Data-Analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.00975","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}