Optimizing Long-Term User Engagement in Short-Video Recommendation via Reinforcement Learning: A Markov Decision Process Framework with Composite Rewards
Informatica · 18.05.2026 · 50 (13)
DOI: 10.31449/inf.v50i13.13064 ↗Kurz gefasst
Fachartikel in der Zeitschrift Informatica, online erschienen am 18.05.2026. Verfasst von Juan Di.
Abstract (Originalsprache)
Under the dynamic condition of short video platforms, the shortfall of conventional recommendation algorithms that pay too much attention to short-term indicators at the cost of long-term user behavior is increasingly obvious. To compensate for it, we utilized a Deep Reinforcement Learning (DRL) approach to develop an intelligent recommendation system framework supported by deep feature engineering, policy updating, and online interaction. We effectively cast the difficult recommendation process into a Markov Decision Process (MDP) in order to improve the user experience by maximizing long-term user value. Experimental findings illustrate that, relative to baseline models like collaborative filtering (MF) and deep neural networks (DNN), our DRL agent possesses a remarkable lead over key long-term engagement indicators, specifically gaining an improvement of more than 22% in average session time. Besides, an ablation study of the reward function confirmed that both immediate and delayed signals are necessary for a composite reward architecture in order to learn a good policy. The findings of this work have repercussions for how short video recommendation intelligence can be boosted and even indicate a new research path for the recommender systems community, shifting away from using short-term metrics towards maximizing long-term user value.
Zitieren
APA
Di, J. (2026). Optimizing Long-Term User Engagement in Short-Video Recommendation via Reinforcement Learning: A Markov Decision Process Framework with Composite Rewards. Informatica, 50(13). https://doi.org/10.31449/inf.v50i13.13064
Vancouver
Di J. Optimizing Long-Term User Engagement in Short-Video Recommendation via Reinforcement Learning: A Markov Decision Process Framework with Composite Rewards. Informatica. 2026;50(13). doi:10.31449/inf.v50i13.13064
BibTeX
@article{Di2026,
author = {Di, Juan},
title = {Optimizing Long-Term User Engagement in Short-Video Recommendation via Reinforcement Learning: A Markov Decision Process Framework with Composite Rewards},
journal = {Informatica},
year = {2026},
volume = {50},
number = {13},
doi = {10.31449/inf.v50i13.13064}
}
EUVIMED