Personalized Hybrid Recommender System with Average Time Intervals

Abstract

Recommendation systems allow users to access contents on their behalf in an overload of information that is the norm in the world of Internet and data. These recommender systems aim to produce the best recommendations that satisfy users’ preferences. The traditional use of collaborative and content-based filtering methods suffers from numerous limitations that hinder their efficacy, but the main issue is not only of the system itself, but of the nature of human interests. The preferences of people are everchanging, and recommendations have to account for the variations. This paper therefore presents a new hybrid method, integrating a parallel collaborative and content-based filtering system with a ranking system based on a user profile with the addition of a time variable to represent the time sensitive characteristic of content and interest. The evaluation of the system in parts shows promising results in the cinematographic field and indicates further potential for development.