feature-importance-analysis

Predicting Late Delivery Risk in Supply Chains using Machine Learning with EDA, feature engineering, and model explainability

Can behavioral & environmental variables predict who survives? End-to-end ML survival analysis for critically endangered Mountain Gorillas. Random Forest with temporal cross-validation, SQL-based EDA, plotnine visualization & demographic risk flagging. Python · scikit-learn

Customer Churn Prediction System using XGBoost Regressor, built on Telecom Industry dataset

Comparative analysis of regression models for predicting building energy demand using supervised machine learning. The compared models are an MLP neural network, RandomForestRegressor, SVR and KNeighborsRegressor. The techniques used include hyperparameter optimization, cross-validation, and feature importance analysis.

A machine learning interpretability project that analyzes and ranks feature importance to understand the variables driving model predictions and improve feature selection strategies.

An Analysis and Machine Learning model to understand employee retention and predict churn as part of the Google Advanced Data Analytics Certificate Capstone Project.

Reproducible, leakage-safe feature selection that works directly on image pixels.

Order‑book liquidity feature engineering + SHAP analysis (XGBoost) with Triple‑Barrier labels; reads OHLCV & depth from SQLite and saves plots to docs/images.

This repository contains code for identifying potential biomarkers of 2022 mpox virus using transcriptomic and machine learning analysis.

Coupling Bootstrap Stability Selection with Leakage-Safe Nested Cross-Validation for Scientific Machine Learning

Identify Top Review Rating Influencers; Forecast Sales

Feature Importance - World's Billionaires

End-to-end machine learning pipeline to predict bank customer churn using Decision Tree and Random Forest, with feature engineering, evaluation, and hyperparameter tuning.

This project explores customer subscription behavior in banking marketing campaigns using the UCI Bank Marketing dataset. It applies machine learning models to predict which customers are likely to subscribe to a term deposit and identifies key demographic, financial, and campaign-related factors that influence customer decisions.

Develops 2 machine learning models that predict which customers are likely to leave the service, and to identify the most influential factors contributing to churn.

Distributed vs. centralized ML for stroke prediction using Apache Spark. Benchmarks a per-partition scikit-learn ensemble (mapPartitions) against MLlib Random Forest, Logistic Regression, and Decision Tree models. Includes speed-up, size-up, and scale-up scalability analysis on a 43K-row clinical dataset.

Explainable AI framework for e-commerce sales prediction and business analytics using Random Forest regression, feature engineering, and permutation feature importance.

Predict telecom customer churn using machine learning models with Python, scikit-learn, and pandas.

scraping premier League 2021-2022 season Data and predicting the result (Win/ Lose) as a classification problem using Gradient Boost and random Forest.

Machine learning for predicting negative cardiac outcomes in patients with atrial fibrillation (AF)