MOVIE RECOMMENDATION SYSTEM USING HYBRID FILTERING WITH WORD2VEC AND RESTRICTED BOLTZMANN MACHINES

Abstract

Recommender systems are designed to provide interesting information to users and assist them in making choices. With the help of a recommender system, users can feel more comfortable using an application. In this final project, we will implement a hybrid filtering method using two techniques: Word2Vec as the algorithm for content-based filtering and Restricted Boltzmann Machine for collaborative filtering. The Word2Vec algorithm will utilize a pre-trained model provided by Google, while the Restricted Boltzmann Machine algorithm will utilize the TensorFlow library. The dataset used for this project will be Movie Lens. The goal of this final project is to evaluate the accuracy and performance of the recommender system using various metrics such as Precision and Normalized Discounted Cumulative Gain.