A High-level Scorecard Modeling API | 评分卡建模尽在于此
-
Updated
Oct 10, 2022 - Python
A High-level Scorecard Modeling API | 评分卡建模尽在于此
Bank-style Credit Risk Scorecard using Logistic Regression, IFRS-9 Expected Credit Loss, and an Interactive Streamlit Risk Dashboard for loan default prediction.
Credit Score Modelling: Perform a Weight of Evidence Logistic Regression Modelling (WoELR) to generate credit scorecard for loan approval with the help of optbinning library.
End-to-end Credit Risk Scorecard Development in Python & SQL. Features Weight of Evidence (WOE) / Information Value (IV) analysis, Logistic Regression modeling, and PD risk segmentation.
Completed as part of the 365 Data Science Credit Risk Modeling in Python Udemy course. Developed an end-to-end credit risk modeling pipeline for consumer lending, covering data preprocessing, feature engineering, Probability of Default , Loss Given Default , Exposure at Default , scorecard development, model validation, population stability
Credit Score Modelling: Perform a Weight of Evidence Logistic Regression Modelling (WoELR) to generate credit scorecard for loan approval.
Consumer credit risk, PD scorecard (logistic regression + WOE/IV) on Home Credit data, with discrimination, calibration and population-stability validation, ongoing monitoring, and model governance. Includes an EAD analysis reframed as a documented data-quality finding.
End-to-End Python implementation of Kanziga et. al's (2026) credit-risk research method: monotonic binning, Weight-of-Evidence encoding, Information Value filtering, residual gradient boosting with hybrid-AUC early stopping, adaptive weighting via a 27-point CV search, Platt calibration, TreeSHAP, DeLong tests & stratified paired bootstrapping.
💰 Credit Risk Scorecard — Gradient Boosting + Logistic Regression + Decision Tree on 5,000 loans. Industry-standard metrics: Gini 0.521 · KS 0.395 · AUC 0.761 · IV/WoE table · Credit grades A-E. Basel III aligned. Production-realistic metrics. Python · scikit-learn
IFRS 9 Credit Risk Scorecard & Expected Credit Loss (ECL = PD * LGD * EAD) Engine under Basel III / EBA standards. Features R Weight of Evidence (WoE) binning & Information Value, Python PD models (Logistic Regression Gini=0.7467 vs XGBoost), 3-Stage Staging, PostgreSQL, automated Excel financial models, and a 2-page Power BI Dashboard.
To associate your repository with the credit-scorecard topic, visit your repo's landing page and select "manage topics."