{"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/modeling-the-intensity-function-of-point","title":"Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks","arxiv_id":"1705.08982","date":"2017-05-24","proceeding":null,"authors":["Shuai Xiao","Junchi Yan","Stephen M. Chu","Xiaokang Yang","Hongyuan Zha"],"abstract":"Event sequence, asynchronously generated with random timestamp, is ubiquitous\namong applications. The precise and arbitrary timestamp can carry important\nclues about the underlying dynamics, and has lent the event data fundamentally\ndifferent from the time-series whereby series is indexed with fixed and equal\ntime interval. One expressive mathematical tool for modeling event is point\nprocess. The intensity functions of many point processes involve two\ncomponents: the background and the effect by the history. Due to its inherent\nspontaneousness, the background can be treated as a time series while the other\nneed to handle the history events. In this paper, we model the background by a\nRecurrent Neural Network (RNN) with its units aligned with time series indexes\nwhile the history effect is modeled by another RNN whose units are aligned with\nasynchronous events to capture the long-range dynamics. The whole model with\nevent type and timestamp prediction output layers can be trained end-to-end.\nOur approach takes an RNN perspective to point process, and models its\nbackground and history effect. For utility, our method allows a black-box\ntreatment for modeling the intensity which is often a pre-defined parametric\nform in point processes. Meanwhile end-to-end training opens the venue for\nreusing existing rich techniques in deep network for point process modeling. We\napply our model to the predictive maintenance problem using a log dataset by\nmore than 1000 ATMs from a global bank headquartered in North America.","url_abs":"http://arxiv.org/abs/1705.08982v1","url_pdf":"http://arxiv.org/pdf/1705.08982v1.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":"modeling-the-intensity-function-of-point","repo_url":"https://github.com/woshiyyya/erpp-rmtpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"modeling-the-intensity-function-of-point","repo_url":"https://github.com/xiaoshuai09/recurrent-point-process","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"point-processes","task_name":"Point Processes"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.08982","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}