zhongqiangwu960812/AI-RecommenderSystem resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2182 stars · 416 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A curated collection of classic recommender system algorithm models with code reimplementations in TensorFlow and PyTorch, paired with blog explanations of the underlying papers and principles. It covers the full industrial recommendation pipeline including recall, coarse ranking, fine ranking (CTR models), and re-ranking, demonstrated on public datasets like MovieLens, Amazon, Criteo, and a news recommendation dataset.

Use cases

• learn classic recommender system algorithms from scratch
• understand CTR prediction models like DeepFM and DIN
• study recall and collaborative filtering techniques
• reimplement recommendation models in TensorFlow or PyTorch
• compare different ranking models on a common dataset
• prepare for recommendation system interviews or competitions
• learn how industrial recommendation funnels work

When to choose

• you want tutorial-style explanations plus runnable code for classic recommendation models
• you are learning recommender systems and want both theory and implementation
• you want to see model structure clearly in simple TensorFlow/PyTorch versions

When to avoid

• you need a production-ready recommendation engine or library
• you want a maintained package with an API rather than educational notebooks
• you need guaranteed correctness or a permissive license for commercial use

Facets

learning-resource · maturity maintenance

machine-learning data-science search-engine machine-learning data-science tutorials python recommender-system collaborative-filtering ctr-prediction deep-learning-models tensorflow pytorch deepctr deepmatch jupyter-notebooks chinese-language algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zhongqiangwu960812/AI-RecommenderSystem")