{"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/mordred-memory-based-ordinal-regression-deep","title":"MOrdReD: Memory-based Ordinal Regression Deep Neural Networks for Time Series Forecasting","arxiv_id":"1803.09704","date":"2018-03-26","proceeding":null,"authors":["Bernardo Pérez Orozco","Gabriele Abbati","Stephen Roberts"],"abstract":"Time series forecasting is ubiquitous in the modern world. Applications range\nfrom health care to astronomy, and include climate modelling, financial trading\nand monitoring of critical engineering equipment. To offer value over this\nrange of activities, models must not only provide accurate forecasts, but also\nquantify and adjust their uncertainty over time. In this work, we directly\ntackle this task with a novel, fully end-to-end deep learning method for time\nseries forecasting. By recasting time series forecasting as an ordinal\nregression task, we develop a principled methodology to assess long-term\npredictive uncertainty and describe rich multimodal, non-Gaussian behaviour,\nwhich arises regularly in applied settings.\n  Notably, our framework is a wholly general-purpose approach that requires\nlittle to no user intervention to be used. We showcase this key feature in a\nlarge-scale benchmark test with 45 datasets drawn from both, a wide range of\nreal-world application domains, as well as a comprehensive list of synthetic\nmaps. This wide comparison encompasses state-of-the-art methods in both the\nMachine Learning and Statistics modelling literature, such as the Gaussian\nProcess. We find that our approach does not only provide excellent predictive\nforecasts, shadowing true future values, but also allows us to infer valuable\ninformation, such as the predictive distribution of the occurrence of critical\nevents of interest, accurately and reliably even over long time horizons.","url_abs":"http://arxiv.org/abs/1803.09704v4","url_pdf":"http://arxiv.org/pdf/1803.09704v4.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":"mordred-memory-based-ordinal-regression-deep","repo_url":"https://github.com/bperezorozco/ordinal_tsf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"astronomy","task_name":"Astronomy"},{"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"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}