# PaddlePaddle/PaddleRec

Recommendation Algorithm大规模推荐算法库，包含推荐系统经典及最新算法LR、Wide&Deep、DSSM、TDM、MIND、Word2Vec、Bert4Rec、DeepWalk、SSR、AITM，DSIN，SIGN，IPREC、GRU4Rec、Youtube_dnn、NCF、GNN、FM、FFM、DeepFM、DCN、DIN、DIEN、DLRM、MMOE、PLE、ESMM、ESCMM, MAML、xDeepFM、DeepFEFM、NFM、AFM、RALM、DMR、GateNet、NAML、DIFM、Deep Crossing、PNN、BST、AutoInt、FGCNN、FLEN、Fibinet、ListWise、DeepRec、ENSFM，TiSAS，AutoFIS等，包含经典推荐系统数据集criteo 、movielens等

Repository: https://github.com/PaddlePaddle/PaddleRec
Canonical: https://ross.abutalabs.com/products/paddlerec
Homepage: https://paddlerec.readthedocs.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ple, deepfm, mmoe, word2vec, gru4rec, tdm, esmm, widedeep, lr
Last push: 2025-04-02T03:22:59+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 14, release rhythm 8, longevity 100
- inputs: {"age_days": 2318, "days_push": 518, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4085, forks 651 (observed 2026-08-28T04:08:34.485365+00:00)

## What it is
PaddleRec is a large-scale recommendation algorithm library built on PaddlePaddle, containing classic and state-of-the-art recommendation models such as LR, Wide&Deep, DeepFM, DIN, DIEN, MMOE, PLE, and many more. It also bundles standard recommendation datasets like Criteo and MovieLens to enable easy benchmarking and experimentation.

## Use cases
- train a CTR prediction model like DeepFM or DIN
- build a multi-task recommendation model with MMOE or PLE
- benchmark recommendation algorithms on Criteo or MovieLens datasets
- implement sequential recommendation with GRU4Rec or BST
- deploy large-scale industrial recommendation models
- learn and prototype recommendation system algorithms

## When to choose
- you want a comprehensive collection of ready-to-use recommendation algorithms in one library
- your team already uses the PaddlePaddle deep learning framework
- you need both classic and cutting-edge recommendation models with standard datasets included
- you are doing research or benchmarking on CTR prediction or multi-task learning for recommendations

## When to avoid
- your stack is built on PyTorch or TensorFlow rather than PaddlePaddle
- you need a full production recommendation system platform rather than an algorithm library
- you only need simple collaborative filtering without deep learning models
- your team has no experience with PaddlePaddle and cannot invest in learning it

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, deep-learning, large-language-models
- platform: python
- tags: recommendation-systems, collaborative-filtering, ctr-prediction, paddlepaddle, deep-learning, algorithms, linux, docker, gpu

## Member repositories
- PaddlePaddle/PaddleRec (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.485365+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 2026-08-29T18:23:23.984064+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/PaddleRec (fetched 2026-08-28T04:08:34.485365+00:00, sha e6db595f1598)
- Data as of 2026-08-30T08:39:29.467469+00:00.