Building Recommender Systems Using Python
summary
Hands-on walkthrough that actually codes three implementations in Python — popularity, classification-style, and item‑based collaborative filtering — using pandas and sparse SVD tools, plus a demo of matrix factorization (SVD) on a toy matrix. Uses a subset of the Million Songs triplets and shows evaluation by precision and recall curves, compares models, explains cold‑start and hybrid fixes, and cites the Netflix matrix (480k × 177k, ~100M ratings ≈ 1% density) as motivation. Code, notebooks and pickled results are provided.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:03Why recommender systems
- 8:38Popularity-based recommenders
- 12:16Classification approach
- 16:00Nearest neighbor CF
- 29:46Matrix factorization
- 37:41Evaluating with precision
- 46:04Demo: song recommender
- 1:25:22Demo: SVD factorization
- 1:36:51Resources and closing
related talks
37mA primer on recommendation systems.
32mLet's talk about Recommendation Systems!
33mPicking What to Watch Next: Build a Recommendation System
20mBuilding Recommender system
01h 31mHands on - Build a Recommender system
58mRecommender Systems – A Walkthrough
31mA practical guide to Singular Value Decomposition in Python
35mHybrid Recommender Systems in Python