{"ID":2880990,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.12665","arxiv_id":"2508.12665","title":"Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network","abstract":"Accurate watch time prediction is crucial for enhancing user engagement in streaming short-video platforms, although it is challenged by complex distribution characteristics across multi-granularity levels. Through systematic analysis of real-world industrial data, we uncover two critical challenges in watch time prediction from a distribution aspect: (1) coarse-grained skewness induced by a significant concentration of quick-skips1, (2) fine-grained diversity arising from various user-video interaction patterns. Consequently, we assume that the watch time follows the Exponential-Gaussian Mixture (EGM) distribution, where the exponential and Gaussian components respectively characterize the skewness and diversity. Accordingly, an Exponential-Gaussian Mixture Network (EGMN) is proposed for the parameterization of EGM distribution, which consists of two key modules: a hidden representation encoder and a mixture parameter generator. We conducted extensive offline experiments on public datasets and online A/B tests on the industrial short-video feeding scenario of Xiaohongshu App to validate the superiority of EGMN compared with existing state-of-the-art methods. Remarkably, comprehensive experimental results have proven that EGMN exhibits excellent distribution fitting ability across coarse-to-fine-grained levels. We open source related code on Github: https://github.com/BestActionNow/EGMN.","short_abstract":"Accurate watch time prediction is crucial for enhancing user engagement in streaming short-video platforms, although it is challenged by complex distribution characteristics across multi-granularity levels. Through systematic analysis of real-world industrial data, we uncover two critical challenges in watch time predi...","url_abs":"https://arxiv.org/abs/2508.12665","url_pdf":"https://arxiv.org/pdf/2508.12665v2","authors":"[\"Xu Zhao\",\"Ruibo Ma\",\"Jiaqi Chen\",\"Weiqi Zhao\",\"Ping Yang\",\"Yao Hu\"]","published":"2025-08-18T06:56:36Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false,"code_links":[{"ID":610750,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2880990,"paper_url":"https://arxiv.org/abs/2508.12665","paper_title":"Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network","repo_url":"https://github.com/BestActionNow/EGMN","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}