Movie Recommender Systems: Implementation and Performance Evaluation

TL;DR

This paper implements and compares various movie recommender system techniques, including collaborative filtering, content-based methods, SVD, and neural networks, to evaluate their performance in predicting user ratings.

Contribution

It provides a comparative analysis of multiple recommendation algorithms implemented in Python for movie rating prediction.

Findings

Neural networks showed improved prediction accuracy.

Collaborative filtering outperformed content-based methods in certain metrics.

SVD-based methods demonstrated strong performance in rating prediction.

Abstract

Over the years, explosive growth in the number of items in the catalog of e-commerce businesses, such as Amazon, Netflix, Pandora, etc., have warranted the development of recommender systems to guide consumers towards their desired products based on their preferences and tastes. Some of the popular approaches for building recommender systems, for mining user, derived input datasets, are: content-based systems, collaborative filtering, latent-factor systems using Singular Value Decomposition (SVD), and Restricted Boltzmann Machines (RBM). In this project, user-user collaborative filtering, item-item collaborative filtering, content-based recommendation, SVD, and neural networks were chosen for implementation in Python to predict the user ratings of unwatched movies for each user, and their performances were evaluated and compared.