Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Article

Download BibTeX

Title

Learning user preferences in livestreaming market: A graphical model considering temporal effect

Authors

[ 1 ] School of Management Science and Engineering, Southwestern University of Finance and Economics, 555, Liutai Avenue, Wenjiang District, Chengdu, Sichuan, 611130, China | [ 2 ] School of Management and Economics, University of Electronic Science and Technology of China, No.2006, Xiyuan Ave, West Hi-Tech Zone, Chengdu, Sichuan, 611731, China | [ 3 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 4 ] Business School, Sichuan University, No.24 South Section 1, Yihuan Road, Chengdu, 610065, China | [ P ] employee

Scientific discipline (Law 2.0)

[2.3] Information and communication technology

Year of publication

2026

Published in

Decision Support Systems

Journal year: 2026 | Journal volume: vol. 202

Article type

scientific article

Publication language

english

Keywords
EN
Abstract

EN The livestreaming market has experienced rapid growth, making effective recommendation systems essential for enhancing user engagement and marketing strategies. Traditional models often fall short in simultaneously capturing user preferences, host popularity, and the temporal dynamics inherent in livestreaming platforms. To address these challenges, we propose an interpretable graphical model that integrates Poisson Factorization with hierarchical structures and explicit temporal effects. Our model jointly learns user preferences and host popularity while accounting for temporal variations. We develop a variational Bayesian inference algorithm for efficient parameter estimation. Using real-world data from a leading livestreaming platform, we demonstrate that our model outperforms several baseline methods in predicting viewing volumes and capturing user–host interactions before, during, and after a public vacation. Additionally, the learned low-dimensional representations enhance predictive tasks, such as payment behavior prediction, and enable effective profiling and segmentation of users and hosts. Our findings provide insights for decision-makers aiming to optimize recommendation systems and marketing strategies in the dynamic livestreaming market.

Date of online publication

05.01.2026

Pages (from - to)

114600-1 - 114600-16

DOI

10.1016/j.dss.2025.114600

URL

https://www.sciencedirect.com/science/article/pii/S0167923625002015

Comments

Article Number: 114600

Ministry points / journal

140

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.