# ibayer/fastFM

fastFM: A Library for Factorization Machines

Repository: https://github.com/ibayer/fastFM
Canonical: https://ross.abutalabs.com/products/fastfm
Homepage: http://ibayer.github.io/fastFM
Language: Python
License: NOASSERTION
License Family: other
Topics: machine-learning, recommender-system, factorization-machines, matrix-factorization
Last push: 2022-07-17T13:12:39+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4328, "days_push": 1508, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1086, forks 204 (observed 2026-08-28T04:03:32.189658+00:00)

## What it is
fastFM is a Python library for Factorization Machines with a scikit-learn compatible API, with performance-critical code written in C and wrapped with Cython. It supports regression, classification, and ranking tasks via SGD, ALS (coordinate descent), and MCMC solvers.

## Use cases
- train factorization machine models for regression
- build recommender systems with matrix factorization
- binary classification with factorization machines
- learning-to-rank with BPR loss
- Bayesian inference for factorization machines with MCMC
- sparse feature interaction modeling in scikit-learn style

## When to choose
- you need factorization machines with a familiar scikit-learn API
- you want multiple solvers (SGD, ALS, MCMC) for regression, classification, or ranking
- you work on Linux or macOS with Python

## When to avoid
- you need Windows support
- you need actively maintained software with recent updates
- you need deep learning based recommenders or GPU acceleration

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, data-science
- domain: machine-learning
- platform: python
- tags: factorization-machines, matrix-factorization, scikit-learn-api, recommender-systems, cython, linux, macos

## Member repositories
- ibayer/fastFM (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:32.189658+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 2026-08-30T06:49:31.790658+00:00, confidence not recorded.
  - readme: https://github.com/ibayer/fastFM (fetched 2026-08-28T04:03:32.189658+00:00, sha e73fe3b10a8e)
  - homepage: http://ibayer.github.io/fastFM (fetched 2026-08-29T12:52:30.756407+00:00, sha f4eeda781f7a)
- Data as of 2026-08-30T08:39:29.467469+00:00.