# interpretml/interpret

Fit interpretable models. Explain blackbox machine learning.

Repository: https://github.com/interpretml/interpret
Canonical: https://ross.abutalabs.com/products/interpret
Homepage: https://interpret.ml/docs
Language: C++
License: MIT
License Family: permissive
Topics: machine-learning, interpretability, gradient-boosting, blackbox, scikit-learn, xai, interpretml, interpretable-machine-learning, interpretable-ai, transparency, iml, interpretable-ml, explainable-ml, explainability, bias, ai, artificial-intelligence, explainable-ai, differential-privacy
Last push: 2026-08-24T16:52:26+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 75, longevity 100
- inputs: {"age_days": 2679, "days_push": 9, "days_rel": 169, "gap_med": 14.5, "n_releases_24m": 21}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6928, forks 787 (observed 2026-08-28T04:09:51.466405+00:00)

## What it is
InterpretML is a Python library that unifies machine learning interpretability techniques, letting users train inherently interpretable glassbox models like the Explainable Boosting Machine and explain blackbox models via global and local explanations. It provides a scikit-learn-compatible API with built-in visualizations for understanding model behavior and individual predictions.

## Use cases
- explain predictions of a blackbox machine learning model
- train an interpretable model as accurate as gradient boosting
- detect bias or fairness issues in my model
- explain a model for regulatory compliance
- debug why my model made a mistake
- visualize global feature importance of a model
- build interpretable models for healthcare or finance

## When to choose
- you need exact, faithful explanations rather than approximations
- you want glassbox models with accuracy competitive with random forests or XGBoost
- you work in a high-stakes domain requiring transparency and auditability
- you want a unified API for both interpretable training and blackbox explanation

## When to avoid
- you only need maximum predictive accuracy with no explanation requirements
- you need deep learning interpretability for neural networks specifically
- your stack is not Python

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-visualization, nlp
- domain: machine-learning, data-science, artificial-intelligence
- platform: python, windows, cross-platform
- tags: explainable-ai, interpretability, xai, glassbox-models, blackbox-explanations, explainable-boosting-machine, ebm, scikit-learn-compatible, model-explanations, fairness, linux, macos

## Member repositories
- interpretml/interpret (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.466405+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 2026-08-29T17:41:24.951154+00:00, confidence not recorded.
  - readme: https://github.com/interpretml/interpret (fetched 2026-08-28T04:09:51.466405+00:00, sha 3ee7ba0a63b8)
  - homepage: https://interpret.ml/docs (fetched 2026-08-29T08:37:16.453056+00:00, sha 535b1b85f277)
  - site_page: https://interpret.ml/docs/interpret.html (fetched 2026-08-29T08:37:16.456195+00:00, sha ebd83be7052f)
  - site_page: https://interpret.ml/docs/python/api/interpret-glassbox.html (fetched 2026-08-29T08:37:16.458242+00:00, sha d0012cbe4c83)
  - site_page: https://interpret.ml/docs/python/api/ExplainableBoostingClassifier.html (fetched 2026-08-29T08:37:16.460482+00:00, sha d42b2b445754)
  - site_page: https://interpret.ml/docs/python/api/ExplainableBoostingRegressor.html (fetched 2026-08-29T08:37:16.463941+00:00, sha 842f76afeb54)
  - site_page: https://interpret.ml/docs/python/api/APLRRegressor.html (fetched 2026-08-29T08:37:16.467389+00:00, sha 6792e83d245b)
  - site_page: https://interpret.ml/docs/python/api/APLRClassifier.html (fetched 2026-08-29T08:37:16.470529+00:00, sha 9372ecec5e85)
  - site_page: https://interpret.ml/docs/python/api/LogisticRegression.html (fetched 2026-08-29T08:37:16.473143+00:00, sha fdf3ae2328c8)
  - site_page: https://interpret.ml/docs/python/api/LinearRegression.html (fetched 2026-08-29T08:37:16.476054+00:00, sha 86a744fd636d)
- Data as of 2026-08-30T08:39:29.467469+00:00.