SHAP-and-LIME-interpretations-for-retail-transcation-customer-data

This repository contains a course assignment for CHE-1148 (Process Data Analytics), with a focus on MLOps, data quality, model drift, and interpretable/explainable machine learning. The included Jupyter Notebook demonstrates the generation of SHAP and LIME plots for a random forest model that predicts client responses to a promotional campaign, aimed at enhancing model interpretability. The HTML file, which needs to be downloaded, displays the output figures for the SHAP and LIME analyses.