In this project, I've built a classification model to predict the probability of default value for a customer based on his credit history and deployed the same as a webapp in Heroku.

This project tackles the crucial challenge of assessing Credit Risk Management in banking. Using Supervised Machine learning, the goal is to predict the probability of default, providing insights into customers' creditworthiness by analyzing variables like account details, purchases, and delinquency information.

Logistic regression-based credit scoring model using public Kaggle data, designed for transparent PD estimation, performance evaluation, and teaching or regulatory use cases.

End-to-end credit risk pipeline: leakage-safe PD modeling, holdout evaluation, and full-portfolio risk band segmentation (50k loans) with stakeholder-ready visuals + Streamlit scoring app.

This model estimates the 12-month Probability of Default (PD) for prime residential mortgage customers in the United Kingdom, aligned with the IFRS 9 impairment framework and calibrated to an adverse macroeconomic scenario. Version 1 (v1) is developed using gradient-boosted decision trees (GBDT)

Probability of default using Machine Learning in R

This repository contains python code from scratch to develop the credit risk model for loan portfolio

Application and behavioural credit risk scoring for Issuer clients — Straive Strategic Consulting

Production-ready PD scorecard model using WoE binning and logistic regression, including discrimination testing (AUC/KS), calibration, PSI stability monitoring, and risk-based decision policy under a Basel-aligned framework.

Credit Risk Probability of Default (PD) Model with Python (ML) and Power BI Model Monitoring Dashboard (KPIs, Confusion Matrix, Predictions)

Production-style Credit Risk Probability of Default (PD) model using 2.9M loan records with time-based validation, XGBoost, KS statistic, and portfolio risk segmentation.

Analysis of the effect of rising interest rates on the probability of default on consumer loans

This repository shows my credit risk analysis (ongoing!) using the dataset Give Me Some Credit (Kaggle, 2011)

Implements the Basel III credit risk framework (PD, LGD, EAD) using Logistic & Linear Regression on Lending Club loan data (2007–2014)

The goal is to build a Probability of Default (PD) model that estimates the customer's risk of default (TARGET=1) as a probability.

End-to-end Credit Risk Scorecard development. Implemented Weight of Evidence (WoE) binning and Information Value (IV) analysis for feature selection. Validated via Basel-III standards using Gini and AUC-ROC metrics.

Credit risk analysis with PD modelling, risk grading and RAROC

Credit Risk Prediction in R

Credit Risk Probability of Default (PD) modelling using Logistic Regression and Random Forest with risk bucket segmentation and threshold optimization.

Commercial credit scorecard (PD) repo for borrower risk grades, score bands, and decision outputs used in both bank-aligned risk assessment and practical origination workflows.