99908 - CREDIT RISK

Learning outcomes

Credit risk is the main source of risk for a commercial bank, far more relevant then other risk types like market, interest, operational, etc.. and can have dramatic systemic effects, as an under estimation of credit risk is at the root of the financial and economic turmoil of the 2008. The course will provide a broad overview of credit risk management in (commercial) banking. First, we will review the methodologies behind the more widely used (structural and reduced form) models for individual credit risk components (EAD,PD,LGD); then we will analyse how credit risk is measured at portfolio level (expected and unexpected losses, risk aggregation and contributions) by the most popular metrics (the Moody’s KMV model, CreditMetrics™ and Credit Risk Plus™). Finally, we will address credit risk regulatory topics, both in terms of capital requirements (Basle II and III) and of accounting standards (IFRS9). The theoretical insight will be paired with practical exercises: some of these models and metrics will be applied to real credits data using the Python scientific stack.

Course contents

1 Introduction to Expected Credit Loss Modelling and Validation

1.1 Introduction

1.2 IFRS 9

1.2.1 StagingAllocation

1.2.2 ECL Ingredients

1.2.3 Scenario Analysis and ECL

1.3 CECL

1.3.1 Loss-Rate Methods

1.3.2 Vintage Methods

1.3.3 Discounted Cash Flow Methods

1.3.4 Probability of Default Methods

1.3.5 IFRS 9 vs. CECL

1.4 ECL and Capital Requirements

1.4.1 Internal Rating-Based Credit Risk-WeightedAssets

1.4.2 How ECLAffects Regulatory Capital and Ratios

2 One-Year PD

2.1 Introduction

2.2 Default Definition and Data Preparation

2.2.1 Default Definition

2.2.2 Data Preparation

2.3 Generalised Linear Models (GLMs)

2.3.1 GLM (Scorecard) Development

2.3.2 GLMCalibration

2.3.3 GLMValidation

2.4 Machine Learning (ML) Modelling

2.4.1 Classification and Regression Trees (CART)

2.4.2 Bagging, Random Forest, and Boosting

2.4.3 ML Model Calibration

2.4.4 ML Model Validation

2.5 Low Default Portfolio, Market-Based, and Scarce Data Modelling

2.5.1 Low Default Portfolio Modelling

2.5.2 Market-Based Modelling

2.5.3 Scarce Data Modelling

3 Lifetime PD

3.1 Introduction

3.2 Data Preparation

3.2.1 Default Flag Creation

3.2.2 Account-Level (Panel) Database Structure

3.3 LifetimeGLMFramework

3.3.1 Portfolio-LevelGLMAnalysis

3.3.2 Account-Level GLM Analysis

3.3.3 LifetimeGLMValidation

3.4 Survival Modelling

3.4.1 KMSurvivalAnalysis

3.4.2 CPH SurvivalAnalysis

3.4.3 AFT SurvivalAnalysis

3.4.4 Survival Model Validation

3.5 Lifetime Machine Learning (ML) Modelling

3.5.1 Bagging, Random Forest, and Boosting Lifetime PD

3.5.2 Random Survival Forest Lifetime PD

3.5.3 LifetimeML Validation

3.6 Transition Matrix Modelling

3.6.1 Naïve Markov Chain Modelling

3.6.2 Merton-Like Transition Modelling

3.6.3 Multi-State Modelling

3.6.4 Transition Matrix Model Validation

4 LGD Modelling

4.1 Introduction

4.2 LGD Data Preparation

4.2.1 LGD Data Conceptual Characteristics

4.2.2 LGD Database Elements

4.3 LGD Micro-Structure Approach

4.3.1 Probability of Cure

4.3.2 Severity

4.3.3 DefaultedAsset LGD

4.3.4 Forward-Looking Micro-Structure LGD Modelling

4.3.5 Micro-Structure Real Estate LGD Modelling

4.3.6 Micro-Structure LGD Validation

4.4 LGD Regression Methods

4.4.1 Tobit Regression

4.4.2 Beta Regression

4.4.3 Mixture Models and Forward-Looking Regression

4.4.4 Regression LGD Validation

4.5 LGD Machine Learning (ML) Modelling

4.5.1 Regression Tree LGD

4.5.2 Bagging, Random Forest, and Boosting LGD

4.5.3 Forward-Looking Machine Learning LGD

4.5.4 Machine Learning LGD Validation

4.6 Hints on LGD SurvivalAnalysis

4.7 Scarce Data and Low Default Portfolio LGD Modelling

4.7.1 Expert Judgement LGD Process

4.7.2 Low Default Portfolio LGD

4.7.3 Hints on How to Validate Scarce Data and Low Default Portfolio LGDs

5 Prepayments, Competing Risks and EAD Modelling

5.1 Introduction

5.2 Data Preparation

5.2.1 How to Organize Data

5.3 Full Prepayment Modelling

5.3.1 Full Prepayment via GLM

5.3.2 Machine Learning (ML) Full Prepayment Modelling

5.3.3 Hints on SurvivalAnalysis

5.3.4 Full Prepayment Model Validation .

5.4 Competing Risk Modelling

5.4.1 Multinomial Regression Competing Risks Modelling

5.4.2 Full Evaluation Procedure

5.4.3 Competing Risk Model Validation

5.5 EAD Modelling

5.5.1 A Competing-Risk-Like EAD Framework

Readings/Bibliography

Primary reference:

Bellini T. ,2019. IFRS 9 and CECL Credit Risk Modelling and Validation: A Practical Guide with Examples Worked in R and SAS. Academic Press - Inprint Elsevier

Additional literature:

Baesens, B., Rosh, D., Scheule, H., 2016. Credit Risk Analytics: Measurement Techniques, Applications, and Examples in SAS.
Wiley, Hoboken

Bellini T., 2017. Stress Testing and Risk Integration in Banks: A Statistical Framework and Practical Software Guide in Matlab and R. Academic Press - Inprint Elsevier

Bellotti, T., Crook, J., 2009. Support vector machines for credit scoring and discovery of significant features. Expert Systems
with Applications 36, 3302–3308

BIS, 2006. Basel II International Convergence of Capital Measurement and Capital Standards: A Revised Framework. BIS,
Basel

Breeden, J.L., Thomas, L.C., 2016. Solution to specification errors in stress testing models. Journal of the Operations Research
Society 67, 830–840

Castren, O., Dees, S., Zaher, F., 2010. Stress-testing euro area corporate default probabilities using a global macroeconomic
model. Journal of Financial Stability 6, 64–74

Dirick, L., Claeskens, G., Baesens, B., 2017. Time to default in credit scoring using survival analysis: a benchmark study. Journal
of the Operational Research Society 68, 652–665

Gordy, M., 2003. A risk-factor foundation for risk-based capital rules. Journal of Financial Intermediation 12, 199–232

IASB, 2014. IFRS 9 Financial Instruments. Technical report, July 2014. International Accounting Standards Board

 

 

 

 

Teaching methods

- Theory presentation: statistical and mathematical approaches 

- Business case on real data

- Exercises in R

Assessment methods

- Business case in R

- Verbal test

Teaching tools

- Exercises and business cases in R

Links to further information

https://www.tizianobellini.com/

Office hours

See the website of Tiziano Bellini