Skip to content

Latest commit

 

History

History
10 lines (9 loc) · 569 Bytes

README.md

File metadata and controls

10 lines (9 loc) · 569 Bytes
Raw

Recommender Systems

Rank-based, Content-Based and Collaborative Filtering

Made articles recommendations to users of the IBM Watson Studio platform on new articles based on previous interactions. In order to determine which articles to show to each user, the following tasks are performed:

  1. Exploratory Data Analysis
  2. Rank Based Recommendations: "Most viewed articles"
  3. User-User Based Collaborative Filtering: "Users like you also viewed.."
  4. Content Based Recommendations: "Articles with similar topic (based on title)"
  5. Matrix Factorization