{"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/dilated-convolutional-neural-networks-for-3","title":"Dilated Convolutional Neural Networks for Time Series Forecasting","arxiv_id":null,"date":"2018-01-02","proceeding":"Journal of Computational Finance, Forthcoming 2018 1","authors":["Anastasia Borovykh ∗ Sander Bohte † Cornelis W. Oosterlee"],"abstract":"We present a method for conditional time series forecasting based on an adaptation of the recent deep\r\nconvolutional WaveNet architecture. The proposed network contains stacks of dilated convolutions that\r\nallow it to access a broad range of history when forecasting, a ReLU activation function and conditioning\r\nis performed by applying multiple convolutional filters in parallel to separate time series which allows for\r\nthe fast processing of data and the exploitation of the correlation structure between the multivariate time\r\nseries. We test and analyze the performance of the convolutional network both unconditionally as well\r\nas conditionally for financial time series forecasting using the S&P500, the volatility index, the CBOE\r\ninterest rate and several exchange rates and extensively compare it to the performance of the well-known\r\nautoregressive model and a long-short term memory network. We show that a convolutional network is\r\nwell-suited for regression-type problems and is able to effectively learn dependencies in and between the\r\nseries without the need for long historical time series, is a time-efficient and easy to implement alternative\r\nto recurrent-type networks and tends to outperform linear and recurrent models.","url_abs":"http://papers.ssrn.com/sol3/Delivery.cfm?abstractid=3272962","url_pdf":"http://papers.ssrn.com/sol3/Delivery.cfm?abstractid=3272962","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":"dilated-convolutional-neural-networks-for-3","repo_url":"https://github.com/RitikaAg/dilated_convolution_network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"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":[{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"wavenet","method_name":"WaveNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}