Research on the Demographic Filtering Machine Learning in Movie Recommendation System

Abstract

In this era of big data explosion, movie recommendation system is widely used as an information tool by human. There are two common issues found in the machine learning movie recommendation system still undeniable: first, cold start, and second, data sparsity. To minimize the issues, a research study is conducted with objective to analyze, study, and test a decision-making algorithm that can solve cold start problem in a movie recommendation system with precise parameter. It involves the implementation of the proposed demographics filtering technique with k-means clustering method using tools like MATLAB, Microsoft Excel, and Microsoft Azure Machine Learning Studio. The research findings shall present the effects of the proposed demographic filtering for movie recommendations. Demographic filtering can group users into clusters based on parameter like gender, age group, and occupation. This research paper shall contribute demographic filtering studies as an alternative solution for the future work of technical development.