Proyek ML untuk segmentasi nasabah bank menggunakan K-Means Clustering dan prediksi segmen dengan model Klasifikasi. Fokus pada analisis perilaku untuk mendukung keputusan bisnis.

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.

End-to-end analysis of bank loan default risk using historical lending data to identify key risk factors, assess borrower behavior, and support data-driven credit decisions.

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.

Machine learning–driven loan default risk prediction dashboard using XGBoost with transparent, case-specific credit risk explanations.

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

Strategic Portfolio Monitor tracking Credit Risk exposure (NPLs) and Digital Channel Migration. Built with SQL Server and Power BI to optimize asset quality.

Customer churn prediction project using EDA, feature engineering, SMOTE balancing, and machine learning models (Random Forest & XGBoost). Includes model evaluation, business insights, and retention strategy recommendations for banking analytics

EDA and visualization of banking loan applicant data to assess credit risk and support data-driven lending decisions.

Loan Default Analysis - Multi-file joins, DateTime operations, String handling, DTI calculations

Banking Churn Dashboard - Risk Segmentation & Retention KPIs using Excel, SQL & Power BI.

Power BI project providing deep insights into UPI data. Features include data cleaning, interactive dashboards, analysis of transaction volumes (by week/day/month), geographic distribution, payment type breakdown, remaining balance by customer age, and key value matrices. Uncover trends and user behavior in the digital payments landscape.

Rules based KYC Risk Scoring Dashboard -SQL and PowerBI. Automates customer classification into Low/Medium/High risk tiers using onboarding data.

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

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

🏦 Modelo predictivo de machine learning para identificar clientes con alta probabilidad de abandono.

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.

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.

Comprehensive analysis of banking transaction data using Power BI to uncover customer behavior patterns