# tensorflow/recommenders

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

Repository: https://github.com/tensorflow/recommenders
Canonical: https://ross.abutalabs.com/products/tensorflow-recommenders
Language: Python
License: Apache-2.0
License Family: permissive
Topics: tensorflow-recommenders, tensorflow, recommender, recommender-system
Last push: 2026-07-08T08:57:55+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 91, release rhythm 67, longevity 100
- inputs: {"age_days": 2259, "days_push": 56, "days_rel": 223, "gap_med": 15, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2027, forks 299 (observed 2026-08-28T04:06:06.958098+00:00)

## What it is
TensorFlow Recommenders is a Python library for building recommender system models on top of TensorFlow and Keras. It covers the full workflow including data preparation, model formulation, training, evaluation, and deployment of recommendation models.

## Use cases
- build a collaborative filtering recommender with TensorFlow
- train a two-tower retrieval model for recommendations
- rank and recommend items to users with Keras
- evaluate top-K recommendation quality
- deploy a recommendation model in production
- build a factorization model on the MovieLens dataset

## When to choose
- you are already using TensorFlow 2.x and Keras
- you need retrieval, ranking, or rating prediction tasks in one library
- you want a gentle learning curve for recommender systems
- you need full workflow support from data prep to deployment

## When to avoid
- your stack is PyTorch-based
- you need lightweight non-deep-learning recommenders like implicit ALS
- you only need simple heuristics without model training

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning
- domain: machine-learning, large-language-models
- platform: python
- tags: recommender-systems, tensorflow, keras, collaborative-filtering, retrieval, ranking

## Member repositories
- tensorflow/recommenders (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.958098+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 2026-08-30T02:59:42.377385+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/recommenders (fetched 2026-08-28T04:06:06.958098+00:00, sha 3bbb48da0723)
- Data as of 2026-08-30T08:39:29.467469+00:00.