# cjlin1/libsvm

LIBSVM -- A Library for Support Vector Machines

Repository: https://github.com/cjlin1/libsvm
Canonical: https://ross.abutalabs.com/products/libsvm
Homepage: https://www.csie.ntu.edu.tw/~cjlin/libsvm/
Language: Java
License: BSD-3-Clause
License Family: permissive
Last push: 2025-12-29T11:23:20+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 59, release rhythm 35, longevity 100
- inputs: {"age_days": 4740, "days_push": 247, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4708, forks 1636 (observed 2026-08-28T04:08:57.336669+00:00)

## What it is
LIBSVM is a widely used library and command-line toolset for support vector machine classification, regression, and distribution estimation, with C/C++, Java, Python, and MATLAB/OCTAVE interfaces. It includes svm-train, svm-predict, and svm-scale tools plus parameter selection utilities like easy.py and grid.py.

## Use cases
- train an SVM classifier on labeled data
- do support vector regression for prediction
- run one-class SVM for anomaly detection
- perform multi-class classification
- select SVM hyperparameters with cross-validation grid search
- scale sparse feature data before training

## When to choose
- you need a proven, efficient SVM implementation with multi-language bindings
- your dataset is small to medium sized and fits in memory
- you want sparse data format support and precomputed kernels
- you need a stable, well-documented classic ML library with BSD license

## When to avoid
- you need deep learning or GPU-accelerated training
- your dataset is very large and SVM training does not scale well
- you want gradient-boosted trees or other modern ML algorithms
- you need an end-to-end ML pipeline framework rather than a single algorithm

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, cli, sdk
- domain: machine-learning, data-science
- platform: cross-platform, cli, python, jvm, cpp, windows
- tags: support-vector-machines, svm, classification, regression, sparse-data, matlab-interface, algorithms, linux, macos

## Member repositories
- cjlin1/libsvm (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:57.336669+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 2026-08-29T18:19:10.047381+00:00, confidence not recorded.
  - readme: https://github.com/cjlin1/libsvm (fetched 2026-08-28T04:08:57.336669+00:00, sha 025800bc5c66)
  - homepage: https://www.csie.ntu.edu.tw/~cjlin/libsvm/ (fetched 2026-08-29T09:03:01.223387+00:00, sha 107a76e37872)
  - site_page: https://www.csie.ntu.edu.tw/~cjlin/libsvm/faq.html (fetched 2026-08-29T09:03:01.226929+00:00, sha 69a8c3fbfe3c)
- Data as of 2026-08-30T08:39:29.467469+00:00.