carla-recourse/CARLA
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
When a machine learning model makes an unfavorable decision, such as denying a loan application, individuals often want to know what they can change to reverse that decision. This project helps researchers and practitioners evaluate and compare different 'algorithmic recourse' methods that explain what input changes would lead to a different outcome. It takes an existing dataset and a trained machine learning model, then helps you assess various methods for generating counterfactual explanations.
300 stars. No commits in the last 6 months.
Use this if you are a researcher or practitioner who needs to understand, evaluate, and benchmark different ways to provide actionable explanations for unfavorable machine learning predictions.
Not ideal if you are looking for a simple, off-the-shelf tool to generate a single counterfactual explanation for an individual case without needing to compare methods.
Stars
300
Forks
65
Language
Python
License
MIT
Last pushed
Oct 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/carla-recourse/CARLA"
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...