JuliaTrustworthyAI/CounterfactualExplanations.jl
A package for Counterfactual Explanations and Algorithmic Recourse in Julia.
This tool helps anyone who uses machine learning models in their work understand why a model made a specific decision. For example, if a loan application was denied, you can input the applicant's data into the model and find out what changes to their profile (like improving their credit score) would lead to an approved loan. This is useful for data scientists, risk analysts, or anyone building or relying on AI systems that impact real-world outcomes.
127 stars.
Use this if you need to explain individual predictions of a black-box machine learning model in a way that suggests actionable changes to achieve a desired outcome.
Not ideal if you are looking for a global explanation of how the entire model works, rather than explanations for specific predictions, or if you don't have access to the model's inner workings (though it can work with black-box models).
Stars
127
Forks
6
Language
Julia
License
MIT
Last pushed
Feb 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JuliaTrustworthyAI/CounterfactualExplanations.jl"
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...