1 Day/ 8 hours Workshop Details:

---

Module 1 (3 hours)

Time	Topic
80min	Data Pre-processing and Credit Scoring Credit scoring techniques for corporate & retail data Outlier detection Standardisation & categorisation Default definitions Non-monotone relations between defaults and risk factors Weight-of-evidence, categorisation, splines Multivariate non-monotone relationship
20min	Break
80min	Probabilities of Default (PD) — Expected PDs Discrete time models (Logit & Probit) Comprehensive modeling including vintage, age and time effects Maximum likelihood estimation Model stability, discrimination & calibration

Module 2 (3 hours):

Time	Topic
80min	Machine Learning Concepts Statistical and Machine Learning thinking Loss functions Train-Test validation split Standardisation and Scaling Bias-Variance tradeoff Oversampling and Undersampling Cross-Validation Hyper-Parameters and Tuning Supervised and Unsupervised Learning Classification and Regression vs. Dimensionality Reduction
20min	Break
80min	Machine Learning Validation Validation framework Backtesting PDs: Discrimination, Calibration, Stability Confusion matrix, ROC curves, AUROC & accuracy ratio Brier scores Binomial test Jefreys prior test Hosmer-Lemeshow Calibration curve and reliability diagram Tests on model stability Portfolio dependence Traffic lights Qualitative validation

Module 3 (2 hours):

Time	Topic
120min	Supervised Machine Learning for PDs — Standalone Techniques Logistic regression K nearest neighbours Decision trees Bagging Random forests Boosting Adaptive Boosting Gradient Boosting Stochastic Gradient Boosting Light GBM Neural Networks

---

Back to In House Training