# datawhalechina/fun-rec

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

Repository: https://github.com/datawhalechina/fun-rec
Canonical: https://ross.abutalabs.com/products/fun-rec
Language: Python
License Family: other
Topics: recommender-system, tensorflow, tianchi-competition, deep-learning, algorithm-engineering, interview-questions, recommendation-algorithms, machine-learning
Last push: 2026-06-27T19:31:01+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 89, release rhythm 35, longevity 100
- inputs: {"age_days": 2215, "days_push": 67, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7295, forks 1027 (observed 2026-08-28T04:09:58.080084+00:00)

## What it is
An open-source Chinese-language textbook (the 'Wheat Book') teaching recommender systems from classic cascade architectures (collaborative filtering, vector/sequence recall, ranking, reranking) to modern generative paradigms (LLM-based, diffusion-based recommendation). Includes a production-grade system project and interview questions, with code in Python and TensorFlow.

## Use cases
- learn recommender systems from scratch
- study generative recommendation with LLMs
- prepare for recommendation algorithm engineer interviews
- understand feature crossing and multi-task ranking models
- build a production-level recommendation system project
- learn diffusion models for recommendation

## When to choose
- you want a structured, free curriculum covering both classic and cutting-edge recommendation techniques
- you read Chinese and prefer textbook-style learning with hands-on projects
- you are preparing for recommendation algorithm engineering roles

## When to avoid
- you need a production-ready recommendation library rather than educational material
- you only read English (though an English README exists, content is primarily Chinese)
- you need stable, versioned content - the project is under active development and changes frequently

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, tutorials, education
- platform: python, cross-platform
- tags: recommender-system, chinese-language, open-textbook, generative-recommendation, collaborative-filtering, tianchi-competition, interview-preparation, recommendation

## Member repositories
- datawhalechina/fun-rec (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:58.080084+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:38:48.272744+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/fun-rec (fetched 2026-08-28T04:09:58.080084+00:00, sha a346716921b0)
- Data as of 2026-08-30T08:39:29.467469+00:00.