Contextual bandits to increase user prediction accuracy in movie recommendation system

Cold-start problems are inevitable phenomena where recommendation systems fail to accurately predict users’ favour and cause the loss of new users. The typical Multi-Armed Bandit (MAB) models are widely adopted as recommendation systems to solve cold-start problems, but standard MAB takes much more...

Full description

Saved in:
Bibliographic Details
Main Author: Chen Yizhe
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:ITM Web of Conferences
Online Access:https://www.itm-conferences.org/articles/itmconf/pdf/2025/04/itmconf_iwadi2024_01018.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705499329560576
author Chen Yizhe
author_facet Chen Yizhe
author_sort Chen Yizhe
collection DOAJ
description Cold-start problems are inevitable phenomena where recommendation systems fail to accurately predict users’ favour and cause the loss of new users. The typical Multi-Armed Bandit (MAB) models are widely adopted as recommendation systems to solve cold-start problems, but standard MAB takes much more recommendation trials than new user’s tolerance. This study adopts Contextual Multi-Armed Bandit (CMAB) to alleviate such situations and compares the performance of CMAB and typical MAB models at an early stage of the cold phase. Overall, CMAB generated better results in 15 trials in terms of cumulative regret and discounted cumulative gain. The optimal number of groups is 10, which alleviates cold-start problems efficiently, and sustains the efficiency of the off-line recommendation system under collaborative filtering. This paper suggests a possible selection of CMAB for recommendation systems to alleviate the cold start problem and estimates the tuned parameters for the MovieLens dataset. The evaluation metric in this paper provides a possible method of analyzing the general performance of a hybrid recommendation system, instead of adopting multiple evaluation metrics respectively, these metrics also provide estimates of the optimal value of parameters.
format Article
id doaj-art-8bd2fa34b1af4b4e972c179f47b57c9c
institution DOAJ
issn 2271-2097
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series ITM Web of Conferences
spelling doaj-art-8bd2fa34b1af4b4e972c179f47b57c9c2025-08-20T03:16:28ZengEDP SciencesITM Web of Conferences2271-20972025-01-01730101810.1051/itmconf/20257301018itmconf_iwadi2024_01018Contextual bandits to increase user prediction accuracy in movie recommendation systemChen Yizhe0Faculty of Science, University of Hong KongCold-start problems are inevitable phenomena where recommendation systems fail to accurately predict users’ favour and cause the loss of new users. The typical Multi-Armed Bandit (MAB) models are widely adopted as recommendation systems to solve cold-start problems, but standard MAB takes much more recommendation trials than new user’s tolerance. This study adopts Contextual Multi-Armed Bandit (CMAB) to alleviate such situations and compares the performance of CMAB and typical MAB models at an early stage of the cold phase. Overall, CMAB generated better results in 15 trials in terms of cumulative regret and discounted cumulative gain. The optimal number of groups is 10, which alleviates cold-start problems efficiently, and sustains the efficiency of the off-line recommendation system under collaborative filtering. This paper suggests a possible selection of CMAB for recommendation systems to alleviate the cold start problem and estimates the tuned parameters for the MovieLens dataset. The evaluation metric in this paper provides a possible method of analyzing the general performance of a hybrid recommendation system, instead of adopting multiple evaluation metrics respectively, these metrics also provide estimates of the optimal value of parameters.https://www.itm-conferences.org/articles/itmconf/pdf/2025/04/itmconf_iwadi2024_01018.pdf
spellingShingle Chen Yizhe
Contextual bandits to increase user prediction accuracy in movie recommendation system
ITM Web of Conferences
title Contextual bandits to increase user prediction accuracy in movie recommendation system
title_full Contextual bandits to increase user prediction accuracy in movie recommendation system
title_fullStr Contextual bandits to increase user prediction accuracy in movie recommendation system
title_full_unstemmed Contextual bandits to increase user prediction accuracy in movie recommendation system
title_short Contextual bandits to increase user prediction accuracy in movie recommendation system
title_sort contextual bandits to increase user prediction accuracy in movie recommendation system
url https://www.itm-conferences.org/articles/itmconf/pdf/2025/04/itmconf_iwadi2024_01018.pdf
work_keys_str_mv AT chenyizhe contextualbanditstoincreaseuserpredictionaccuracyinmovierecommendationsystem