Jul 3, 2019 · Artificial Intelligence

Improving Recommendation Diversity with Determinantal Point Processes and Greedy Optimization

The article explains how recommendation systems balance exploitation and exploration, introduces diversity metrics such as temporal, spatial, and coverage, and presents a determinantal point process (DPP) based algorithm accelerated by Cholesky decomposition and greedy inference, demonstrating significant speedups and improved relevance‑diversity trade‑offs in experiments.

DiversityRecommendation Systemscholesky decomposition

0 likes · 10 min read

Improving Recommendation Diversity with Determinantal Point Processes and Greedy Optimization

Hulu Beijing

Oct 12, 2018 · Artificial Intelligence

How Hulu Boosted Recommendation Diversity with Determinantal Point Processes

This article explains how Hulu tackled the trade‑off between accuracy and diversity in its massive video recommendation system by applying Determinantal Point Processes and an efficient incremental greedy algorithm, achieving 100× speed‑ups without sacrificing recommendation quality.

DiversityHuluRecommendation Systems

0 likes · 7 min read

How Hulu Boosted Recommendation Diversity with Determinantal Point Processes