# christophM/interpretable-ml-book

Book about interpretable machine learning

Repository: https://github.com/christophM/interpretable-ml-book
Canonical: https://ross.abutalabs.com/products/interpretable-ml-book
Homepage: https://christophm.github.io/interpretable-ml-book/
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2026-07-07T14:17:17+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 8, longevity 100
- inputs: {"age_days": 3451, "days_push": 57, "days_rel": 538, "gap_med": null, "n_releases_24m": 1}
- 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 5364, forks 1101 (observed 2026-08-28T04:09:16.087829+00:00)

## What it is
The source repository for Christoph Molnar's book 'Interpretable Machine Learning: A Guide for Making Black Box Models Explainable', written in Jupyter Notebooks and published free online. It covers interpretable models and model-agnostic explanation methods such as LIME, Shapley values, permutation feature importance, and accumulated local effects.

## Use cases
- learn how to explain black box machine learning models
- understand LIME and Shapley values
- find a guide to interpretable machine learning techniques
- study model-agnostic interpretation methods
- learn about feature importance and accumulated local effects
- reference material for explainable AI research

## When to choose
- you want a comprehensive, free, well-regarded reference on model interpretability
- you are a data scientist or ML practitioner needing to explain model predictions
- you want critical, in-depth discussion of interpretation methods' strengths and weaknesses

## When to avoid
- you need a software library or tool rather than a book
- you want hands-on code tutorials for a specific framework
- you need a formal textbook with exercises for a course

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, nlp, data-science, documentation
- domain: machine-learning, artificial-intelligence, data-science, tutorials
- platform: python, cross-platform
- tags: explainable-ai, xai, book, lime, shapley-values, model-interpretation, jupyter-notebook, web-server

## Member repositories
- christophM/interpretable-ml-book (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:16.087829+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 2026-08-29T17:58:44.282635+00:00, confidence not recorded.
  - readme: https://github.com/christophM/interpretable-ml-book (fetched 2026-08-28T04:09:16.087829+00:00, sha 3f52f111e577)
  - homepage: https://christophm.github.io/interpretable-ml-book/ (fetched 2026-08-29T08:53:01.331845+00:00, sha 3c884fba4ac6)
- Data as of 2026-08-30T08:39:29.467469+00:00.