{"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/detpp-leveraging-object-detection-for-robust","title":"DeTPP: Leveraging Object Detection for Robust Long-Horizon Event Prediction","arxiv_id":"2408.13131","date":"2024-08-23","proceeding":null,"authors":["Ivan Karpukhin","Andrey Savchenko"],"abstract":"Long-horizon event forecasting is critical across various domains, including retail, finance, healthcare, and social networks. Traditional methods, such as Marked Temporal Point Processes (MTPP), often rely on autoregressive models to predict multiple future events. However, these models frequently suffer from issues like converging to constant or repetitive outputs, which limits their effectiveness and general applicability. To address these challenges, we introduce DeTPP (Detection-based Temporal Point Processes), a novel approach inspired by object detection techniques from computer vision. DeTPP employs a unique matching-based loss function that selectively prioritizes reliably predictable events, improving the accuracy and diversity of predictions during inference. Our method establishes a new state-of-the-art in long-horizon event forecasting, achieving up to a 77% relative improvement over existing MTPP and next-K methods. The proposed hybrid approach enhances the accuracy of next event prediction by up to 2.7% on a large transactional dataset. Notably, DeTPP is also among the fastest methods for inference. The implementation of DeTPP is publicly available on GitHub.","url_abs":"https://arxiv.org/abs/2408.13131v2","url_pdf":"https://arxiv.org/pdf/2408.13131v2.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":"detpp-leveraging-object-detection-for-robust","repo_url":"https://github.com/ivan-chai/hotpp-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"detpp-leveraging-object-detection-for-robust","repo_url":"https://github.com/ivan-chai/torch-linear-assignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"point-processes","task_name":"Point Processes"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-processes-on-agegroup-transactions-mtpp","task":"Point Processes","dataset":"AgeGroup Transactions MTPP","model":"DeTPP","rank_in_archive_order":1,"of":5,"metrics":{"OTD":"6.66","T-mAP":"9.17"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-amazon-mtpp","task":"Point Processes","dataset":"Amazon MTPP","model":"DeTPP","rank_in_archive_order":1,"of":4,"metrics":{"OTD":"5.98","T-mAP":"37.18"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-retweet-mtpp","task":"Point Processes","dataset":"Retweet MTPP","model":"DeTPP","rank_in_archive_order":1,"of":6,"metrics":{"OTD":"134.4","T-mAP":"57.37"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-stackoverflow-mtpp","task":"Point Processes","dataset":"StackOverflow MTPP","model":"DeTPP","rank_in_archive_order":1,"of":3,"metrics":{"OTD":"12.06","T-mAP":"23.11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.13131","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}