This project created various types of recommendation systems to recommend articles to both new and returning users, based on real data from the IBM Watson Studio platform.
-
Exploratory data analysis
- Used descriptive statistics and visuals to understand the dataset
- Clean up the dataset
-
Rank-based recommendation for new users
- Created functions to recommend most popular articles
-
User-user based collaborative filtering for existing users
- Created functions to recommend articles based on what similar users liked
-
User-item based collaborative filtering for existing users
- Implemented singular value decoposition (SVD) to recommend articles based on the history of user-article interactions
- Trained SVD on training set and evaluated performance on testing set.
Recommendations_with_IBM.ipynb
: code and markdownsdata
articles_community.csv
: data of articles contentuser-item-interactions.csv
: data of user-article interactions
Udacity Nanodegree program in partner with IBM Watson Studio.