jpmorganchase/cf-shap-facct22
Counterfactual Shapley Additive Explanation: Experiments
This project helps AI researchers and data scientists reproduce specific experiments related to counterfactual explanations for machine learning models. It takes raw financial and other tabular datasets, processes them, trains models, and then generates and evaluates counterfactual explanations. The output includes plots and tables illustrating the performance and characteristics of these explanations.
No commits in the last 6 months.
Use this if you are an AI researcher or data scientist looking to replicate the experimental results on counterfactual explanations presented in the associated academic paper.
Not ideal if you are looking for a ready-to-use library to implement counterfactual explanation algorithms, as this repository is specifically for experiment reproduction.
Stars
11
Forks
7
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jul 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jpmorganchase/cf-shap-facct22"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shap/shap
A game theoretic approach to explain the output of any machine learning model.
mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
iancovert/sage
For calculating global feature importance using Shapley values.
aerdem4/lofo-importance
Leave One Feature Out Importance
predict-idlab/powershap
A power-full Shapley feature selection method.