{"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-1","title":"Temporal Attention Augmented Bilinear Network for Financial Time Series Data Analysis","arxiv_id":null,"date":"2019-05-05","proceeding":"IEEE Transactions on Neural Networks and Learning Systems 2019 5","authors":["Dat Thanh Tran","Alexandros Iosifidis","Juho Kanniainen","Moncef Gabbouj"],"abstract":"Financial time-series forecasting has long been a\r\nchallenging problem because of the inherently noisy and stochastic\r\nnature of the market. In the high-frequency trading,\r\nforecasting for trading purposes is even a more challenging task,\r\nsince an automated inference system is required to be both\r\naccurate and fast. In this paper, we propose a neural network\r\nlayer architecture that incorporates the idea of bilinear projection\r\nas well as an attention mechanism that enables the layer to\r\ndetect and focus on crucial temporal information. The resulting\r\nnetwork is highly interpretable, given its ability to highlight the\r\nimportance and contribution of each temporal instance, thus\r\nallowing further analysis on the time instances of interest. Our\r\nexperiments in a large-scale limit order book data set show\r\nthat a two-hidden-layer network utilizing our proposed layer\r\noutperforms by a large margin all existing state-of-the-art results\r\ncoming from much deeper architectures while requiring far fewer\r\ncomputations.","url_abs":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8476227&casa_token=MDY9tPmpRaIAAAAA:QuHmwRMKJjxMA9rP6kQ2gZFhLQLPP-Onznm68JItDNJEoy_Y5QBYRZtodLC84j7PqvzwzMM&tag=1","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8476227&casa_token=MDY9tPmpRaIAAAAA:QuHmwRMKJjxMA9rP6kQ2gZFhLQLPP-Onznm68JItDNJEoy_Y5QBYRZtodLC84j7PqvzwzMM&tag=1","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-1","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-classification","task_name":"Time Series Classification"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}