Zoom Training Details:

Day 1:

Duration	Topic
80 min	LGD engineering Introduction into Python Outlier detection Standardisation & categorisation The role of LGD and EAD in credit loss modeling Computing observed LGD LGD discount rates Resolution bias Discount rates COVID-19 challenges
20 min	Break
80 min	Loss Given Default (LGD) Concepts Statistical and machine learning thinking Workflow in machine learning Loss functions Train-test validation split Standardisation and scaling Bias-variance trade-off Cross-validation Hyper-parameters and tuning Supervised and unsupervised learning Classification and regression vs. dimensionality reduction Marginal modeling (linear, fractional logit & beta regressions) PD-LGD models

Day 2:

Duration	Topic
80 min	Payoff and Exposure Concepts Payoff and expected lifetime modeling Conversion measures at default and undistressed period Credit lines & flexible repayment schedules Backtesting LGD and EAD
20 min	Break
80 min	Machine Learning Validation Validation framework Backtesting LGDs: discrimination, calibration, stability Sccuracy, ROC curves, AUC & accuracy ratio Brier scores R^2 Calibration curve and reliability diagram Portfolio dependence

Day 3:

Duration	Topic
80 min	Current expected credit losses (CECL) for US GAAP and IFRS 9 Loan loss provisioning and Basel capital 12-month expected loss vs. lifetime expected loss Rating class formation and roll rate analysis Macroeconomic forecasts Multi-period PD forecasts based on the macroeconomy and lifecycle Prediction of lifetime expected losses Significant increase in credit risk (SICR)
20 min	Break
80 min	Supervised Machine Learning for LGDs Regression K Nearest Neighbours Decision Trees Bagging and Boosting

Day 4:

Duration	Topic
80 min	Unexpected Credit Losses Basel Calibrations Asset Correlation modelling Asymptotic Single Risk Factor Model Simulations Value-at-Risk and Expected Shortfall
20 min	Break
80 min	Supervised Machine Learning for LGDs Neural networks Deep learning Support Vector Regressions

---

Back to Zoom Training