Credit Risk Modelling & Credit Scoring with Machine Learning

Building credit risk assessment model and predicting credit score with logistic regression, random forest, and KNN

Created by: Christ Raharja
Ex Technology Risk Consultant, and E-commerce enthusiast

What Will I Learn?

• Learn how to build credit risk assessment model using logistic regression
• Learn how to build credit risk assessment model using random forest
• Learn how to build credit risk assessment model using K Nearest Neighbor
• Learn how to predict credit score using decision tree regressor
• Learn how to find correlation between debt to income ratio and default rate
• Learn how to analyze relationship between loan intent, loan amount, and default rate
• Learn how to analyze relationship between outstanding debt and credit score
• Learn how to deploy machine learning model using Gradio
• Learn the basic fundamentals of credit risk analysis, technical limitations in credit risk modelling, and credit risk assessment use cases in banking industries
• Learn how credit risk assessment models work. This section will cover data collection, preprocessing, feature selection, train test split, and model training
• Learn about factors that affect credit score, such as payment history, credit utilization ratio, length of credit history, outstanding debt, and credit mix
• Learn how to evaluate the accuracy and performance of the model using precision, recall, and cross validation
• Learn how to find and download credit dataset from Kaggle
• Learn how to clean dataset by removing missing values and duplicates

Requirements

• No previous experience in credit risk modelling is required
• Basic knowledge in Python and finance

Target audience

• People who are interested in building credit risk assessment model using machine learning
• People who are interested in predicting credit score using machine learning