Fortune-500-grade banking analytics platform: OLTP -> medallion lakehouse -> Kimball star schema -> semantic layer -> 9-tab executive dashboard + 5 ML models (churn, fraud, segmentation, forecasting). Production-ready, governed, fully tested.

Capstone project: employee engagement vs customer satisfaction vs branch performance (R, regression, clustering, Shiny)

📊 Banking Analytics Dashboard built with Power BI — exploring customer demographics, financial health, transaction behavior & card insights across 4 analytical pages with DAX-powered KPIs.

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.

End-to-end bank customer churn prediction — EDA, feature engineering, Random Forest & Gradient Boosting models, interactive Streamlit app. Built with Python, Scikit-learn & Plotly.

End-to-end banking campaign analytics project using Power BI, SQL, Python, and statistical analysis to uncover customer behavior, campaign performance, engagement patterns, risk insights, and macroeconomic impact on subscription conversion.

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.

📊 Predict loan defaults reliably using a hybrid ensemble of machine learning models for enhanced accuracy and real-time insights in credit risk assessment.

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

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.

End-to-end Canadian Credit Risk & PD modeling project using public Canadian lending data, ML models, SHAP explainability, Streamlit UI, and Power BI dashboard.

Banking & Credit Analytics Dashboard: Analysis of 400M+ AZN loan portfolio using Power BI & AI (Key Influencers). Focused on interest rate optimization and branch performance.

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

Analyzed bank loan application and repayment data using sql and power bi to evaluate approval trends, risk factors, and loan performance.

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

🏦 Credit Card Fraud Detection System using Random Forest & XGBoost with SMOTE | 284K transactions | ROC-AUC 0.98 | End-to-end ML pipeline with EDA, preprocessing, model training, evaluation & fraud alert simulation

End-to-end ML project for detecting fraudulent credit card transactions using Random Forest, SMOTE, and an interactive Streamlit dashboard.

This Power BI project analyzes banking loan performance to identify credit risk patterns, default drivers, repayment behavior, and high-risk customer segments. The dashboard provides actionable insights for risk managers and credit policy teams.

Retail banking analysis covering customers, accounts, transactions, loans, cards, and service feedback using SQL, Python, and Power BI.

Customer churn is one of the most critical KPIs any business tracks. This project digs into churn patterns across dimensions like geography, age, gender, credit score, and credit card status — giving decision-makers a clear visual picture of which customer segments are most at risk.