Recommendation system project, an assignment for a grad level course in Fall 2019
In this project, I created a recommender engine, evaluated its performance, and made changes to improve performance wherever applicable. The data used was the MovieLens 100K Dataset which contains 100,000 movie ratings from 943 users and a selection of 1682 movies.
There are 7 main parts in this assignment project: data preprocessing and baseline algorithms (i.e. popularity and user average), similarity in collaborative filtering, collaborative filtering, probabilistic matrix factorization(PMF), performance comparison, similarity evaluation, and testing with different user types.