An end-to-end ML application that predicts bank customer churn using 9 different models and provides AI-generated retention strategies with Groq LLM. Built with Streamlit for interactive predictions and visualizations.

Built and deployed a Flask-based machine learning system to predict loan default risk using customer demographics and financial indicators. Applied advanced ensemble models like XGBoost and LightGBM to achieve ~99% accuracy. Designed a full-stack solution with real-time prediction capabilities, enabling faster, smarter loan decisions in banking.

Predict loan approvals using machine learning with SHAP explainability. Analyze customer data, build interpretable models, and visualize feature impact for business decision support.

"Predicting loan approval outcomes using machine learning models on applicant data to assist in risk-aware decision-making."

Enterprise ML system for banking customer churn prediction (91% accuracy). Delivers actionable retention insights with production-ready implementation including comprehensive testing and deployment options for real-world business impact.

Time series modelling and FTE planning based on loan application data from a Big 4 Australian bank

This project explores customer behavior using the Bank Marketing dataset to predict term deposit subscriptions. It includes EDA, feature engineering, model training, class imbalance handling, and evaluation using a logistic regression model.

This repository showcases a proof of concept of my work at Bartronics India Ltd containing Power BI dashboards and a custom SQL stored procedure developed for monitoring Banking Correspondent (BC) performance, transaction trends and rural banking KPIs in the Financial Inclusion System.