Movie Recommendation Algorithm Based on Ensemble Learning

Abstract

With the rapid development of personalized services, major websites have launched a recommendation module in recent years. This module will recommend information you are interested in based on your viewing history and other information, thereby improving the economic benefits of the website and increasing the number of users. This paper has introduced content-based recommendation algorithm, K-Nearest Neighbor (KNN)-based collaborative filtering (CF) algorithm and singular value decomposition-based (SVD) collaborative filtering algorithm. However, the mentioned recommendation algorithms all recommend for a certain aspect, and do not realize the recommendation of specific movies input by specific users which will cause the recommended content of the website to deviate from the need of users, and affect the experience of using. Aiming at this problem, this paper combines the above algorithms and proposes three ensemble recommendation algorithms, which are the ensemble recommendation of KNN + text, the recommendation of user KNN + movie KNN, and the recommendation of user KNN + singular value decomposition. Compared with the traditional collaborative filtering algorithm based on matrix factorization, the method we proposed can realize the recommendation of specific movies input by specific users and make more personalized recommendations and can deal with the problem of cold start and sparse matrix processing issues to a certain extent.

HABE: hybrid AdaBoost ensemble method of probabilistic matrix factorization recommendation system

“…Ensemble learning has also been utilized to improve the precision of recommendation systems. In their research, Fang Yuke et al [4] incorporated the user similarity-based recommendation approach, employed various similarity measures to generate diverse recommendation models, and combined them by assigning weights to obtain the ultimate prediction score. This approach improved the model's prediction accuracy.…”

Movie recommendation model based on probabilistic matrix decomposition using hybrid AdaBoost integration

“…The idea of integrated learning has also been adopted to increase the accuracy of the recommendation system. Fang, Fu & Zhou (2011) integrated the recommendation method based on user similarity, used different similarity measures to generate different recommendation models, and weighted the sum to obtain the final prediction score, which improved the model’s prediction accuracy. Yan, Qi & Pang (2020) constructed a new dataset by combining user-based and product-based prediction score differences with actual scores and then trained the XG-boost model on the dataset.…”

Research on Personalized Recommendation System of New Media Short Video Based on Big Data Mining

“…It models user interests by analyzing user behavior. Simply put, it means analyzing current preferences based on users' past preferences, in order to predict their interests and make recommendations to them [2]. The essence of personalized recommendation is information filtering, which filters personalized information to meet users' needs from the dynamic information flow.…”