What they didn’t teach you in Grad School #bbuzz
summary
Implements a well‑cited ALS recommender (4416 citations) on the 26 million ratings MovieLens set using an off‑the‑shelf Apache Spark implementation, and finds top recommendations dominated by items with one rater. Production fix is simple and pragmatic: filter out films rated by fewer than 500 people, which yields sensible recommendations and meets business metrics. Emphasizes tradeoffs between novelty (publications) and maintainable, fast solutions that actually work in production.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 0:25PhD
- 1:10Whats different
- 2:04Structure
- 3:06Academia
- 4:00Algorithm
- 4:46Example
- 5:22Offtheshelf
- 7:39Recommendation Engine
- 8:54Recommendations Engine
- 9:18Recommendations Filtering
- 9:47Personal Incentives
- 10:15Impact on supervisors
- 10:40Impact on industry
- 11:33Limits to progress
related talks
01h 48mRecommendation engines explained
33mPicking What to Watch Next: Build a Recommendation System
01h 21mUnlocking Personalization: A Deep Dive into Modern Recommendation Algorithms
37mA primer on recommendation systems.
37mBuild a Recommender System in Apache Spark and Integrate it Using Akka
38mBuilding Recommender System in PHP8
57mHands-On with LLM-Powered Recommenders: Hybrid Architectures
01h 31mHands on - Build a Recommender system