Machine Learning for Credit Risk Python-Beginner to Advanced

Build real Machine Learning models for Credit Risk using Python: PD, LGD, EAD, IFRS 9, Basel and Explainability
What you'll learn
Understand how Machine Learning is applied in Credit Risk modelling, including PD, LGD, EAD and IFRS 9 concepts, from both business and technical perspectives.
Develop end-to-end Python skills to build, train, validate and explain ML models for credit portfolios using real datasets and industry techniques.
Develop end-to-end Python skills to build, train, validate and explain ML models for credit portfolios using real datasets and industry techniques.
Learn to implement feature engineering, model evaluation (ROC/KS/GINI/Brier), SHAP explainability, and deployment pipelines using FastAPI and SQL.
Apply ML to real banking case studies including retail PD, SME LGD, EAD/CCF, and stress-testing.
Apply ML to real banking case studies including retail PD, SME LGD, EAD/CCF, and stress-testing.
Requirements
Basic understanding of Excel or numbers (no advanced skills required)
No prior programming experience needed - all Python concepts are taught step-by-step
A general interest in credit risk, finance, data analytics, or machine learning
A general interest in credit risk, finance, data analytics, or machine learning
Description
This course contains the use of artificial intelligence.Machine Learning is transforming the way banks and financial institutions assess credit risk, build predictive models, and make lending decisions. This course teaches you how to apply Machine Learning techniques to Probability of Default (PD), Loss Given Default (LGD), Exposure at Default (EAD), and Expected Credit Loss modelling using Python.Designed for both beginners and experienced professionals, the course covers every step required to build production-ready credit risk solutions. You will learn not only how to code these models, but also how they fit into real-world risk management, IFRS 9 provisioning, Basel capital modelling, and stress-testing environments.Throughout the program, you will build hands-on models using practical Python examples and clearly structured workflow lessons.You will learn how to:• Build supervised Machine Learning models for PD, LGD, and EAD predictions• Perform data preparation, data cleaning, and feature engineering• Apply model performance metrics such as ROC, KS, Gini, and Brier Score• Evaluate and compare models using logistic regression, tree-based methods, and boosting algorithms• Use model explainability techniques including SHAP-based interpretation• Create ML pipelines to train, score, and monitor production models• Set up basic deployment concepts such as APIs, dashboards, and data feeds• Understand risk governance expectations for model validation and transparency• Connect ML concepts to real-world credit risk decisioning and portfolio managementThe course includes structured examples and practical case studies such as retail PD modelling, LGD estimation examples, EAD modelling challenges, and credit portfolio stress-testing demonstrations.By the end of this course, you will be able to:• Build real Machine Learning solutions in Python• Understand end-to-end model development in a financial risk setting• Communicate results to analysts, stakeholders, and risk managers• Apply modern ML methods in credit analytics, portfolio monitoring, and modelling projectsNo prior Python programming experience is required. All coding concepts are introduced step-by-step, making this course accessible to motivated beginners, while offering advanced depth for experienced analysts, quants, and risk professionals.This training is ideal for learners who want to upgrade their technical modelling capabilities and build confidence applying Machine Learning in real financial environments.
Who this course is for
Credit Risk Analysts who want to upgrade from Excel/SAS to Python and Machine Learning
Banking and Finance professionals looking to understand modern credit modelling techniques
Data Analysts and aspiring Data Scientists interested in building real ML models used in banks
Students or graduates aiming for roles in Risk, Analytics, FinTech, or Quantitative Finance
Professionals preparing for IFRS 9, Basel, or credit-risk related projects
Homepage