An accelerated way to hands-on masterclasses in Python for machine learning for credit risk analytics. Together we will master practical credit risk analytics and build credit risk models from scratch
Topics you don't want to miss:
Demystify machine learning techniques and learn how to successfully apply them for credit risk prediction using real data
"Boost" your PD models
Learn how to program decision trees, random forests, neural networks (and more) for default and PD prediction from scratch
See how efficient feature selection is implemented
Compare and interpret various train/test/validation-split strategies specific for credit risk
Create your own cross-validation strategies
Apply various under-/over-/synthetic-sampling strategies
Learn how to compare model outputs: stability, discrimination (ROC and CAP) and calibration
Forecasting PDs: TTC and PIT
LGDs: discount rates and selection bias
Prepayment models for mortgage and corporate loans
CECL and IFRS 9 models for multi-period risks
Please bring your Python-enabled laptops. Codes will be provided in electronic form. No prior Python skills required
Outcomes:completion of the Masterclass, you will:
Be able to build your own credit risk models in Python from real world credit data
Have a good understanding of current challenges in the credit risk industry
Understand merits and pitfalls of various approaches
Learning by programming
Discussions and networking with other analysts in small groups
Receive a confirmation of 12 hours of continuing professional development
...and much more using using REAL mortgage data, over 1,500 lines of code and documentation...
Comments by recent participants:
"I found the Credit Risk Analytics course run by Dr Harry Scheule highly informative, practical, and interesting. The course is structured to suit participants with little prior experience in credit risk modelling while accommodating needs of professionals who want to expand their understanding in the application of credit risk models. All example models in the course are run by using real-life mortgage and corporate loan data to be relevant. As an added bonus, participants are provided with Python, SAS and R codes for a range of credit risk models that can be used, with some tweaks as necessary, for estimating probabilities of default and loss given default, stress testing, and IFRS 9 provisioning after completing the course."
Specialist, Australian Prudential Regulation Authority
"I attended this workshop in Sydney in March. It is now coming to other locations! It is extremely useful if you are modeling PD-LGD-EAD for stress-testing, Basel II/Basel III/CCAR/CECL/IFRS9 with a lot of hands-on examples in Python, SAS and R. It is bound to be of benefit to you whether you are a beginner or a seasoned credit risk modeler."