In this talk, we discuss the paper “N-BEATS: Neural basis expansion analysis for interpretable time series forecasting” by B. Oreshkin et al., ICLR, 2020.<\/p>\n
Abstract<\/strong><\/p>\n We focus on solving the univariate times series point forecasting problem using deep learning. We propose a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers. The architecture has a number of desirable properties, being interpretable, applicable without modification to a wide array of target domains, and fast to train. We test the proposed architecture on several well-known datasets, including M3, M4 and TOURISM competition datasets containing time series from diverse domains. We demonstrate state-of-the-art performance for two configurations of N-BEATS for all the datasets, improving forecast accuracy by 11% over a statistical benchmark and by 3% over last year’s winner of the M4 competition, a domain-adjusted hand-crafted hybrid between neural network and statistical time series models. The first configuration of our model does not employ any time-series-specific components and its performance on heterogeneous datasets strongly suggests that, contrarily to received wisdom, deep learning primitives such as residual blocks are by themselves sufficient to solve a wide range of forecasting problems. Finally, we demonstrate how the proposed architecture can be augmented to provide outputs that are interpretable without considerable loss in accuracy.<\/p>","excerpt":"","slug":"journal-club-jinwoo-hyun","image":false,"all_day":false,"start_date":"2025-12-26 10:00:00","start_date_details":{"year":"2025","month":"12","day":"26","hour":"10","minutes":"00","seconds":"00"},"end_date":"2025-12-26 12:00:00","end_date_details":{"year":"2025","month":"12","day":"26","hour":"12","minutes":"00","seconds":"00"},"utc_start_date":"2025-12-26 01:00:00","utc_start_date_details":{"year":"2025","month":"12","day":"26","hour":"01","minutes":"00","seconds":"00"},"utc_end_date":"2025-12-26 03:00:00","utc_end_date_details":{"year":"2025","month":"12","day":"26","hour":"03","minutes":"00","seconds":"00"},"timezone":"Asia\/Seoul","timezone_abbr":"KST","cost":"","cost_details":{"currency_symbol":"$","currency_code":"USD","currency_position":"prefix","values":[]},"website":"","show_map":true,"show_map_link":true,"hide_from_listings":false,"sticky":false,"featured":false,"categories":[{"name":"Journal Club","slug":"journal-club","term_group":0,"term_taxonomy_id":219,"taxonomy":"tribe_events_cat","description":"","parent":231,"count":209,"filter":"raw","id":219,"urls":{"self":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/tribe\/events\/v1\/categories\/219","collection":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/tribe\/events\/v1\/categories","up":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/tribe\/events\/v1\/categories\/231"}}],"tags":[],"venue":{"id":7007,"author":"3","status":"publish","date":"2022-12-11 21:14:12","date_utc":"2022-12-11 12:14:12","modified":"2022-12-11 21:14:12","modified_utc":"2022-12-11 12:14:12","url":"https:\/\/www.ibs.re.kr\/bimag\/venue\/b232-seminar-room-ibs\/","venue":"B232 Seminar Room, IBS","slug":"b232-seminar-room-ibs","address":"55 Expo-ro Yuseong-gu","city":"Daejeon","country":"Korea, Republic of","province":"Daejeon","zip":"34126","website":"https:\/\/www.ibs.re.kr","stateprovince":"Daejeon","json_ld":{"@type":"Place","name":"B232 Seminar Room, IBS","description":"","url":"","address":{"@type":"PostalAddress","streetAddress":"55 Expo-ro Yuseong-gu","addressLocality":"Daejeon","addressRegion":"Daejeon","postalCode":"34126","addressCountry":"Korea, Republic of"},"telephone":"","sameAs":"https:\/\/www.ibs.re.kr"},"show_map":true,"show_map_link":true,"global_id":"www.ibs.re.kr\/bimag?id=7007","global_id_lineage":["www.ibs.re.kr\/bimag?id=7007"]},"organizer":[{"id":3971,"author":"3","status":"publish","date":"2021-02-23 18:10:12","date_utc":"2021-02-23 09:10:12","modified":"2021-02-23 18:10:12","modified_utc":"2021-02-23 09:10:12","url":"https:\/\/www.ibs.re.kr\/bimag\/organizer\/jae-kyoung-kim\/","organizer":"Jae Kyoung Kim","slug":"jae-kyoung-kim","email":"jaekkim@kaist.ac.kr","json_ld":{"@type":"Person","name":"Jae Kyoung Kim","description":"","url":"","telephone":"","email":"jaekkim@kaist.ac.kr","sameAs":""},"global_id":"www.ibs.re.kr\/bimag?id=3971","global_id_lineage":["www.ibs.re.kr\/bimag?id=3971"]}],"custom_fields":[],"json_ld":{"@context":"http:\/\/schema.org","@type":"Event","name":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting – Jinwoo Hyun","description":"<p>In this talk, we discuss the paper "N-BEATS: Neural basis expansion analysis for interpretable time series forecasting" by B. Oreshkin et al., ICLR, 2020. Abstract We focus on solving the … <\/p>\\n<p class="link-more"><a href="https:\/\/www.ibs.re.kr\/bimag\/event\/journal-club-jinwoo-hyun\/" class="more-link">Continue reading<span class="screen-reader-text"> "N-BEATS: Neural basis expansion analysis for interpretable time series forecasting – Jinwoo Hyun"<\/span><\/a><\/p>\\n","url":"https:\/\/www.ibs.re.kr\/bimag\/event\/journal-club-jinwoo-hyun\/","eventAttendanceMode":"https:\/\/schema.org\/OfflineEventAttendanceMode","eventStatus":"https:\/\/schema.org\/EventScheduled","startDate":"2025-12-26T10:00:00+09:00","endDate":"2025-12-26T12:00:00+09:00","location":{"@type":"Place","name":"B232 Seminar Room, IBS","description":"","url":"","address":{"@type":"PostalAddress","streetAddress":"55 Expo-ro Yuseong-gu","addressLocality":"Daejeon","addressRegion":"Daejeon","postalCode":"34126","addressCountry":"Korea, Republic of"},"telephone":"","sameAs":"https:\/\/www.ibs.re.kr"},"organizer":{"@type":"Person","name":"Jae Kyoung Kim","description":"","url":"","telephone":"","email":"jaekkim@kaist.ac.kr","sameAs":""},"performer":"Organization"}}