Home▸AI & Machine Learning▸Recommendation Engine Lab: Collaborative Filtering, Matrix Factorisation and Diversity Re-ranking

🛒 Recommendation Engine Lab: Collaborative Filtering, Matrix Factorisation and Diversity Re-ranking

Build a shop with hidden shopper tastes, train popularity, content, item-based, matrix-factorisation and hybrid recommenders, measure precision, NDCG and coverage on held-out purchases, and run an A/B test in a 3D embedding space.

AI & Machine Learning3DModerate60 FPS📱 Mobile-adapted⇄ 2D version
Recommendation Engine Lab: Collaborative Filtering, Matrix Factorisation and Diversity Re-ranking ↗ Open standalone
⚙ Under the hood

Train popularity, content, item-based, matrix-factorisation and hybrid recommenders on a synthetic shop with hidden shopper tastes, score them on held-out purchases (precision, NDCG, coverage) and run an A/B test in a 3D embedding.

Recommender SystemsCollaborative FilteringMatrix FactorisationMachine LearningA/B Testing

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)