charmlab/recourse_benchmarks
A package for Displaying and Computing Benchmarking Results of Algorithmic Recourse and Counterfactual Explanation Algorithms
When a machine learning model makes an important decision that negatively impacts someone — like denying a loan or flagging a medical test — this tool helps understand why and how to change the outcome. It takes in various datasets and common ML models to calculate 'algorithmic recourse,' showing what specific features (e.g., credit score, income) need to change for a favorable decision. This is for researchers and practitioners in fields where ML models have high-stakes implications for individuals.
Use this if you need to evaluate, compare, or develop different methods for providing actionable advice to individuals affected by unfavorable machine learning predictions.
Not ideal if you are looking for a simple, out-of-the-box solution to directly apply recourse in a production system without understanding the underlying methods.
Stars
8
Forks
6
Language
Python
License
MIT
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/charmlab/recourse_benchmarks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...