Home▸Machine Learning & Neural Networks▸How Recommendation Engines Decide What You See

🎯 How Recommendation Engines Decide What You See

An interactive 3D user-item embedding space where adjusting a simulated user's interaction history shows collaborative-filtering recommendations shifting toward nearby items.

Machine Learning & Neural Networks3DModerate60 FPS

An interactive 3D user-item embedding space where adjusting a simulated user's interaction history shows collaborative-filtering recommendations shifting toward nearby items in the embedding space.

🔬 What It Demonstrates

Users and items live as points in a shared learned space; recommendations are simply the nearest items to a user's position, and an explore/exploit slider trades relevance for discovery of new tastes.

🎮 How to Use

Pick a genre the simulated user has been watching, raise history strength to move them out of the cold-start centre, then tune Top-K and exploration to see the recommendation beams update live.

💡 Did You Know?

Production recommenders use hundreds of embedding dimensions, but the underlying geometry is exactly this: nearest neighbours in a learned space, with a pinch of randomness for exploration.

⚙ Under the hood

Interactive 3D user-item embedding space where adjusting a simulated user's interaction history shows collaborative-filtering recommendations shifting toward nearby items in the embedding space.

recommendation-enginescollaborative-filteringpersonalizationembeddingsrecsysmachine-learning

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