Saved in:
Bibliographic Details
Main Authors: Zhao, Xu, Ma, Ruibo, Chen, Jiaqi, Zhao, Weiqi, Yang, Ping, Hu, Yao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.12665
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915787695980544
author Zhao, Xu
Ma, Ruibo
Chen, Jiaqi
Zhao, Weiqi
Yang, Ping
Hu, Yao
author_facet Zhao, Xu
Ma, Ruibo
Chen, Jiaqi
Zhao, Weiqi
Yang, Ping
Hu, Yao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network
Zhao, Xu
Ma, Ruibo
Chen, Jiaqi
Zhao, Weiqi
Yang, Ping
Hu, Yao
Information Retrieval
H.3.3
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.
title Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network
topic Information Retrieval
H.3.3
url https://arxiv.org/abs/2508.12665