Soojung Lee, Journal of Internet Computing and Services, Vol. 25, No. 5, pp. 87-94, Oct. 2024
10.7472/jksii.2024.25.5.87, Full Text:  HTML
Keywords: Recommender System, Collaborative Filtering, Similarity Measure, genetic algorithm

Abstract

A collaborative filtering-based recommender system is a method that gives priority to items preferred by similar neighbors when providing recommended items for the current user. The similarity measure is very important for the performance of the system. In this study, a genetic algorithm was used to calculate the similarity value between users that results in optimal performance. In particular, the genetic algorithm was run separately for each rated item feature to improve prediction accuracy performance. Through performance experiments, the optimal probabilities of the genetic algorithm operators were obtained, and as a result of experiments using two types of public datasets, it was confirmed that the prediction performance of the proposed method was superior to that of existing methods, especially in a sparse data environment. The results of this study can improve the accuracy of personalized recommendations and be effectively applied in real-world applications with large-scale user and item data.

Statistics
Cite this article