Recommendation System Using Deep Learning

Recommendation systems are a commom feature of many services nowadays. Using a significant quantity of user history that has been stored, this system forecasts what a user will use next. Recommendation systems are frequently used in a variety of industries, including e-commerce, social services and movies. We are attempting to compare three distinct deep learning models—RBM, Autoencoder, and DNN and comparing their efficiency in order to determine which model will perform best given the supplied dataset. We conducted experiments on real world data like MovieLens, which has four csv files to compare the efficacy of different Deep Learning models. These experimental results show that the query features and item features which Deep Neural Network can readily incorporate may help identify a user' s interests and increase the relevancy of recommendations.