What it does
InterpretML helps people see why a machine learning model makes its predictions. It can train 'glassbox' models, whose reasoning is visible, and explain 'blackbox' models, whose inner workings are hidden.
Its main model, the Explainable Boosting Machine, was developed at Microsoft Research. Its makers say it is about as accurate as popular blackbox methods while giving exact explanations.
The README says this helps with debugging models, spotting unfair treatment, meeting legal rules and high-stakes uses like healthcare and finance.
Who it's for
Data scientists and researchers who need to explain or check what their models are doing.
Can I use it without coding?
Developers only. It is a Python library used from code. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Linux, Mac, Windows
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and ValuesResearch paper · Jun 2022
- InterpretML: A Unified Framework for Machine Learning InterpretabilityResearch paper · Sept 2019