← Back to portfolio
Recommendation Engine
Collaborative filtering recommender combining content-based and hybrid approaches.
Problem
Users facing too many choices need relevant items surfaced automatically, not buried in an unfiltered catalog.
Approach
Built a collaborative filtering recommendation system using matrix factorization and cosine similarity, then extended it with content-based and hybrid approaches for more personalized recommendations.
Results
- Delivered both collaborative-filtering and hybrid recommendation approaches
Want the full picture, or think this kind of work fits a role you're hiring for?