Explainable AI using SHAP & CXPlain

About

Machine Learning (ML) based models are often black-box
To use ML model in industrial setting it should be fair and reliable
Metrics like accuracy-score or r2-score makes it reliable, but one cannot say anything about the fairness of the model
ML engineer should be able to explain their models and understand the value and accuracy of their findings
In this project, we have tried to interpret a trained ML model using CXPlain and SHAP library
This project was developed for a #hackingforfuture Hackathon organized by International Center for Networked, Adaptive Production ICNAP in coorperation with the Fraunhofer Project Center at the University of Twente

A ML model is trained on a tabular dataset for binary classification task
Using this trained model, feature importance for the input features are calculated with the help of CXPlain and SHAP model interpretation library
Results are compared quantitatively.

pip install cxplain
pip install shap
pip install pycaret
pip install tensorflow
pip install plotly

Light Gradient Boosting Machine Classification Report

Light Gradient Boosting Machine Confusion Matrix

Relative importance of features using SHAP

Relative importance of features using CXPlain