# aksnzhy/xlearn

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

Repository: https://github.com/aksnzhy/xlearn
Canonical: https://ross.abutalabs.com/products/xlearn
Homepage: https://xlearn-doc.readthedocs.io/en/latest/index.html
Language: C++
License: Apache-2.0
License Family: permissive
Topics: machine-learning, statistics, data-science, data-analysis, factorization-machines, ffm, fm
Last push: 2023-08-28T05:14:10+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": 3371, "days_push": 1101, "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 3090, forks 516 (observed 2026-08-28T04:07:42.319512+00:00)

## What it is
xLearn is a high-performance C++ machine learning package implementing linear models (LR), factorization machines (FM), and field-aware factorization machines (FFM), with Python and CLI interfaces. It is optimized for large-scale sparse data, offering out-of-core training, cross-validation, and early stopping.

## Use cases
- train factorization machines on click-through rate data
- predict CTR for online advertising
- build recommendation models from sparse user-item features
- train FFM models for Kaggle-style competitions
- fit logistic regression on high-dimensional sparse features
- train models on datasets larger than memory via out-of-core learning

## When to choose
- you need fast FM/FFM training on large sparse datasets
- you are replacing liblinear, libfm, or libffm with a faster alternative
- you want a simple Python or CLI interface without heavy dependencies
- your data is too big for memory and you need out-of-core training

## When to avoid
- you need deep learning or neural network models
- you need GPU acceleration
- you need actively developed features or recent community support
- you need dense-data or general-purpose ML beyond linear/FM models

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning
- domain: machine-learning, data-science
- platform: cpp, python, cli, cross-platform
- tags: factorization-machines, field-aware-factorization-machines, linear-models, sparse-data, libffm, libfm, click-through-prediction, recommendation

## Member repositories
- aksnzhy/xlearn (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:42.319512+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 2026-08-29T18:46:28.582613+00:00, confidence not recorded.
  - readme: https://github.com/aksnzhy/xlearn (fetched 2026-08-28T04:07:42.319512+00:00, sha 2d8cdc86a6c8)
- Data as of 2026-08-30T08:39:29.467469+00:00.