{"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/data-normalization-for-bilinear-structures-in-1","title":"Data Normalization for Bilinear Structures in High-Frequency Financial Time-series","arxiv_id":null,"date":"2021-01-10","proceeding":null,"authors":["Abstract—Financial time-series analysis and forecasting have been extensively studied over the past decades","yet still remain as a very challenging research topic. Since the financial market is inherently noisy and stochastic","a majority of financial timeseries of interests are non-stationary"],"abstract":"Abstract—Financial time-series analysis and forecasting have\r\nbeen extensively studied over the past decades, yet still remain\r\nas a very challenging research topic. Since the financial market\r\nis inherently noisy and stochastic, a majority of financial timeseries\r\nof interests are non-stationary, and often obtained from\r\ndifferent modalities. This property presents great challenges\r\nand can significantly affect the performance of the subsequent\r\nanalysis/forecasting steps. Recently, the Temporal Attention augmented\r\nBilinear Layer (TABL) has shown great performances\r\nin tackling financial forecasting problems. In this paper, by\r\ntaking into account the nature of bilinear projections in TABL\r\nnetworks, we propose Bilinear Normalization (BiN), a simple,\r\nyet efficient normalization layer to be incorporated into TABL\r\nnetworks to tackle potential problems posed by non-stationarity\r\nand multimodalities in the input series. Our experiments using\r\na large scale Limit Order Book (LOB) consisting of more than\r\n4 million order events show that BiN-TABL outperforms TABL\r\nnetworks using other state-of-the-arts normalization schemes by\r\na large margin.","url_abs":"https://ieeexplore.ieee.org/abstract/document/9412547?casa_token=4pOo00u7DEoAAAAA:KCfvDPG0hL-BJJrU2FNqPDPlV9j-FNOmenLN5evEQMnNxshEvgW92BaLG95iQ3G3sPlI9m4","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9412547","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":"data-normalization-for-bilinear-structures-in-1","repo_url":"https://github.com/LeonardoBerti07/Data-Normalization-for-Bilinear-Structures-in-High-Frequency-Financial-Time-series-BiN-TABL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}