Inheriting Thompson Sampling for Movie Recommendation

Junyan Shi

2024

Abstract

This paper is committed to solving the problem of selecting movie genres for movie recommendation through historical rating analysis. For the recommendation problem, it is well known that using the Thompson Sampling(TS) algorithm is a very good method. However, the traditional Thompson Sampling deals with a Bernoulli invariant problem but the movie-recommended problem is a non-Bernoulli and continuously changing problem. So, this study improves the Thompson Sampling algorithm with the concept of inheritance to fit the movie recommendation problem. The research replaces the Beta distribution of the Thompson Sampling algorithm with a normal distribution and introduces an inheritance proportion to inherit the experience. The Inheritance Thompson Sampling helps cinema owners decide in real-time which genre of movie to play to improve the mean rating of the movies in the cinema. The research findings indicate that, compared to the Thompson Sampling algorithm, the Inheritance Thompson Sampling can reduce the total regret by 50% to 30%.

Paper Citation

in Harvard Style

Shi J. (2024). Inheriting Thompson Sampling for Movie Recommendation. In Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI; ISBN 978-989-758-713-9, SciTePress, pages 559-563. DOI: 10.5220/0012958800004508

in Bibtex Style

@conference{emiti24,
author={Junyan Shi},
title={Inheriting Thompson Sampling for Movie Recommendation},
booktitle={Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI},
year={2024},
pages={559-563},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012958800004508},
isbn={978-989-758-713-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI
TI - Inheriting Thompson Sampling for Movie Recommendation
SN - 978-989-758-713-9
AU - Shi J.
PY - 2024
SP - 559
EP - 563
DO - 10.5220/0012958800004508
PB - SciTePress