Recommender system has a great impact commercially. Ranging from online shopping websites like Amazon to online video streaming website like Youtube or movie streaming website like Netflix, all of these tech giants have develop their own recommender systems that help them to improve their customer experience.
In this project, two recommender systems will be implemented: Collaborative Filtering Recommender System & Content Based Filtering Recommender System
- Data Manipulation: numpy, pandas, collections, csv
- Data Visualization: matplotlib
- Machine Learning: tensorflow, scikit-learn
Datasets used for collaborative filtering can be found in the data folder.
Datasets used for content filtering can be downloaded at https://grouplens.org/datasets/movielens/latest/.
- 9,742 movies rated by 610 users, and 100,836 ratings
- Dataset after pre-processing: 3,649 movies rated by 610 users, and 90274 ratings
- Recommend items to you based on ratings of users who gave similar ratings as you
- Recommend items to you based on features of user and item to find good match
