Credit Risk Modeling for Basel II Using SAS
Duration: 4.0 days CEU: 2.4
Presented by Bart Baesens, Ph.D. or Christophe Mues, Ph.D., Assistant Professors at the School of Management of the University of Southampton (UK)
In this course, students learn how to develop credit risk models in the context of the recent Basel II guidelines. The course provides a sound mix of both theoretical and technical insight, as well as practical implementation details. These are illustrated by several real-life case studies.
Learn how to
- develop PD, LGD, and EAD models for Basel II
- validate and stress-test Basel II models
- ensure your organization is in compliance.
Who should attend
Anyone involved in building scoring/predictive credit risk systems, or responsible for validating and monitoring their behavior and performancePrerequisites
Before attending this course, you should- have business expertise in credit scoring and an understanding of statistical classification methods. Previous SAS software and SAS Enterprise Miner experience is helpful but not necessary.
- contact instructor Bart Baesens directly if you have questions: Bart.Baesens@econ.kuleuven.be.
Course Contents
Review of Basel I and Basel II- the Basel I and Basel II regulation
- standard approach versus IRB approach for credit risk
- PD versus LGD versus EAD
- the Merton/Vasicek model for calculating the regulatory capital
- application scoring, behavioral scoring, and profit scoring
- bankruptcy prediction models
- selecting the sample
- segmentation
- reject inference
- exploratory data analysis
- outlier detection and treatment
- missing values
- weight of evidence coding and information value
- basic concepts of classification
- classification techniques: logistic regression, decision trees, linear programming, k-nearest neighbor, cumulative logistic regression
- input selection, such as filters, stepwise regression, and p-values
- setting the cut-off
- measuring scorecard performance
- splitting up the data: single sample, holdout sample, cross-validation
- performance metrics, such as ROC curve, CAP curve, and KS-statistic
- defining ratings
- scorecard implementation
- modeling loss given default (LGD)
- defining LGD, such as market approach and work-out approach
- time weighted versus default weighted versus exposure weighted LGD
- choosing the discount factor and the workout period
- dealing with incomplete workouts
- economic downturn LGD
- modeling LGD using segmentation
- modeling LGD using regression
- shaping the Beta distribution for LGD
- modeling exposure at default (EAD): estimating credit conversion factors (CCF)
- cohort/fixed time horizon/momentum approach for CCF
- risk drivers for CCF
- CAP curves for LGD and CCF
- correlations between PD, LGD, and EAD
- calculating expected loss (EL)
- validating PD, LGD, and EAD models
- quality control
- quantitative versus qualitative validation
- use testing
- through-the-cycle (TTC) versus point-in-time (PIT) validation
- backtesting for PD, LGD, and EAD
- backtesting statistics, such as binomial, Vasicek, and chi-squared
- traffic light indicator approach
- backtesting action plans
- stress testing for PD, LGD, and EAD models
- static versus dynamic stress testing
- correlated trend analysis
- monitoring PD, LGD, and EAD models
- segmenting PD, LGD, and EAD models
- benchmarking
- internal versus external benchmarking
- Kendall's tau and Kruskal's gamma for benchmarking
- scorecard management
- low default portfolios (LDPs): implementation and validation
- value-at-risk (VaR) models
- the Merton/Vasicek model for calculating the regulatory capital
- review of traditional techniques for scorecard development
- neural networks: the neuron model, multilayer perceptrons (MLPs), training an MLP
- support vector machines: the SVM classification model and building scorecards using SVMs (short)
- case study: using logistic regression and support vector machines to develop a country rating system
- survival analysis for developing customer lifetime models
- the censoring problem
- survival curves versus hazard curves
- Kaplan Meier analysis
- parametric survival analysis
- proportional hazards regression
- using survival analysis for LGD modeling and profit scoring
Software Addressed
This course addresses the following software product(s): SAS Enterprise Miner, SAS for Enterprise Risk Management.Course Materials
Students receive a hardcopy of the course notes and, in some courses, can choose to take home a copy of the course data.U.S. Schedule
| 27JAN2009 New York, NY | 01JUN2009 San Francisco, CA |
Check for additional and updated schedule information online at support.sas.com/courses/basel53.html.