Udemy Business

Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

IFRS 9 PIT & Lifetime PD Modelling (SAS, English Course)

Name: IFRS 9 PIT & Lifetime PD Modelling (SAS, English Course)
Rating: 4.1 (43 reviews)

Advanced IFRS 9 credit risk modelling in English — expert course with SAS, real data, and banking insights

Created byTaipa Gibon Huchu

Last updated 11/2025

English

What you'll learn

Build and calibrate Point-in-Time Probability of Default (PIT PD) models using SAS to align with observed default experience.
Apply forward-looking macroeconomic adjustments by integrating GDP, unemployment, interest rates, and other drivers into PD forecasts.
Implement multiple scenario approaches (base, upside, downside) with probability weighting to generate robust IFRS 9 Expected Credit Loss (ECL) estimates.
Develop automated SAS frameworks and macros for PIT PD modelling, calibration, scenario generation, and audit-ready reporting.
Design Lifetime PD models using transition matrices and survival analysis, and link them to ECL calculation engines.
Ensure regulatory compliance with IFRS 9 and Basel guidelines, including staging (SICR), documentation, and model validation best practices.

Course content

13 sections • 182 lectures • 15h 28m total length

Welcome to Professional Credit Risk Modelling2:14
Introduction to IFRS 9 and PIT PD4:25
IFRS 9 PIT PD Modelling4:59
IFRS9 Three Pillar Overview5:36
Modelling Process2:32
Data Loading to SAS3:29
Data Quality Overview3:03
IFRS 9 PIT PD Model Development and ECL1:40
Splitting Data3:39
Feature Engineering2:04
Logistic Regression2:54
KS Statistic & AUC2:03
Model Calibration1:40
ECL Calculation1:54
Observation and Performance Window UPDATE SAS DEMO4:21
Loading the updated dataset DEMO8:54
Conclusion2:18
In this lecture, we introduce the IFRS 9 standard and its role in credit risk management.
Download the attached student notes (PDF) for a structured summary of the key points.
By the end, you’ll understand the purpose, scope, and regulatory context of IFRS 9.
Module 1 - 5 Quiz Questions – Introduction to IFRS 9

Introduction to data preparation and data checks3:00
Data Preparation4:11
Performance and Observation Windows4:21
Performance Window Example4:48
Vintage Analysis4:45
Wholesale Variables4:39
Retail Variables4:25
oversampling5:13
Data Quality4:11
Data Quality Procedures in SAS4:25
Mean Median Imputation2:44
Missing Data5:10
Handling Missing Values4:13
Missing Data Treatment3:05
Binary Indicator2:16
Working With Missing Values2:59
Cluster4:30
Rule Based2:38
Using Proc Logistic to handle Missing Data4:41
Regression3:38
Hot Deck2:00
Data Quality Summary3:30
Module Conclusion1:49
Section 2 – Data Preparation and Quality Checks
Learn how to prepare raw credit risk datasets for modeling. This includes handling missing data, variable formatting, and ensuring data quality through automated checks
Module 2– 5 Quiz Questions

Variable Selection and Model Development3:21
Exploratory Data analysis4:28
Exploratoy Data Analysis4:37
Multicollearity4:28
PROC VARCLUS3:22
Feature Engineering4:30
PROC VARCLUS Demo2:29
Variable Relavance3:51
Coarse Classing & Fine Classing4:43
Coarse and Fine Classing Demo4:03
Spearman & Hoeffdieng D Statistics3:55
Spearman & Hoeffding D Demo3:09
Variable Selection4:18
Stepwise Backward Forward Selection5:25
Variable Interactions3:40
Interactions3:49
Odds Ratio3:33
Model Development3:31
PROC LOGISTIC5:09
Logistic Regression5:08
Logistic Regression Demo3:44
Categorical Variables5:26
Grouping Categorical Variables Demo3:50
Greenacre method4:41
Greenacre Demo4:02
Testing logit linearity2:14
Lagged Variables3:18
Module Conclusion1:14
Quiz 3 – 5 Quiz questions : Variable Selection & Logistic Regression Modules

Module Introduction2:55
Overview of Model Validation4:58
Loading and Spliting dataset DEMO2:53
Train , Score & Validate Datasets DEMO2:50
AUC & ROC4:51
ROC and AUC DEMO2:26
Gini coefficient & Lift Chat4:03
KS and Gains & Lift Curve DEMO6:03
Hosmer & Lemeshow5:09
Barrier Score4:05
Decile Ranking4:17
Brier , Hosmer and Lemeshow Method DEMO5:29
AIC BIC & 2 LL5:03
D Statistic Concordance4:54
Associations and Fit Statistics10:42
Model Evaluation & rerun4:00
PSI4:55
PSI and Monitoring Framework8:06
Performance Summary4:37
Cross Validation5:07
Summary and Conclusion3:51
Quiz 4 - 5 Questions – Model Development & Evaluation (IFRS 9 PD Models)

PIT PD Calibration2:54
Forecasting and Scenario Analysis3:38
Stagging Overlay4:54
1PIT PD Calibration & Forward-Looking Adjustments4:44
Implementaion in SAS -PIT PD Calibration & Forward-Looking Adjustments5:21
Scenario Weighting4:44
PIT PD (12M) Calibration in SAS4:17
Calibration-in-the-Large & Platt Scaling4:23
Calibration-in-the-Large & Platt Scaling DEMO6:29
Macro Forecasting and Scenario Calibration4:30
Macro Overlay in PD Calibration5:06
Section Conclusion1:50
Quiz 5– 5 Questions : Forecasting, Calibration & Scenario Analysis

Introduction2:30
survival model3:23
Cox Proportional Hazards5:33
Censoring3:25
Survival Functions3:29
Cox Regression in SAS3:44
Cohort Vintage Modelling4:34
Cohort Analysis2:58
Transition Matrices3:35
PROC IML Transition Matrices3:31
ECL Using Lifetime_PD3:46
Benefits of Lifetime PD4:07
PIT vs Lifetime_PD Stage Transitions3:50
Cox Survival & PD Derivation DEMO4:26
Cohort Analysis DEMO2:08
Transition Matrix DEMO4:54
section Conclusion2:02
Quiz 7– 5 Questions : Lifetime PD Modelling (IFRS 9)

Loss Given Default LGD The Missing Link in Credit Risk6:36
Data Preparation for LGD Modelling10:23
Linear Regression LGD Model9:10
Beta and Fractional Response Regression10:52
Inflated Beta Regression for Loss Given Default10:09
Mixed Effects LGD Model11:14
Model Validation and Comparison10:57
IFRS 9 and Basel Integration of LGD12:54
End-to-End LGD Modelling Case Study11:37
LGD Modelling Recap and Transition to ECL9:00
OLS Logit Transform DEMO12:29
BETA Regression PROC glimmix DEMO5:29
Quantile Regression DEMO6:03
LGD Decision Tree PROC HPSPLIT DEMO7:17
LGD Random Forest DEMO5:40
LGD Fractional logit PROC nlmixed DEMO5:48
LGD Beta Mixed PROC glimmix DEMO7:03
LGD Zero One Inflated Beta Regression DEMO7:15

Exposure at Default Modelling8:39
Understanding Credit Conversion Factors CCF10:26
Data Preparation for EAD Modelling11:00
Linear and Log Linear EAD Regression Models11:45
Tobit and Truncated Regression for EAD11:00
Beta and Fractional Response Regression for EAD12:14
Credit Conversion Factor CCF Modelling Regression and Logistic Approaches14:13
Validation and Back Testing of EAD Models11:05
IFRS 9 and Basel Integration of EAD12:03
End-to-End EAD Modelling Case Study12:47
EAD Recap and Transition to Expected Credit Loss ECL11:20

Introduction2:39
Regulatory ECL Reporting5:03
ECL Profit and Loss5:38
Classification Pillar5:15
12-Month Expected Credit Loss (ECL)3:35
Lifetime Expected Credit Loss (ECL) Part 16:09
Advanced Portfolio Aggregation & Risk Insights4:17
Lifetime Expected Credit Loss (ECL) Part 24:57
IFRS 9 Regulatory Reporting & Disclosures8:02
Sensitivity Analysis and Section Conclusion5:24
ECL Calculation DEMO4:52
Congratulations1:49
Quiz 8 – 5 Questions : IFRS 9 ECL Validation, Reporting & Sensitivity

Requirements

Basic understanding of credit risk or finance concepts is helpful, but not mandatory.
Familiarity with statistics (probabilities, regressions, distributions) will make it easier to follow the modelling sections.
Some exposure to SAS is recommended, but all code will be explained step by step.
Learners should have access to SAS Studio (free trial or academic edition) or other SAS IDE
Most importantly: a willingness to learn, practice, and apply concepts in real-world credit risk modelling.

Description

Important Notice

This is an advanced, expert-level English course .
It assumes prior knowledge of credit risk and programming (SAS/Python/R).

If you are a beginner, please take a foundation-level IFRS 9 course before this one.

AI Voice Disclaimer: The lectures are narrated using an AI-generated voice for clarity and consistency.

Who This Course Is For (Intended Learners)

This course is for you if:

You are a Credit Risk Analyst / Data Scientist working in banking or financial services.
You are preparing for IFRS 9, Basel 3.1, or regulatory model validation roles.
You already know logistic regression, survival analysis, or credit risk basics, and want to apply them in SAS/Python.

Not for beginners in finance or programming.

Requirements / Prerequisites

Strong background in statistics / econometrics.
Familiarity with credit risk concepts (PD, LGD, EAD, staging).
Working knowledge of SAS, Python, or R.
Basic understanding of financial regulations (IFRS 9, Basel II/III) is recommended.

What You’ll Learn (Learning Objectives)

By the end of this expert-level course in English, you will:

Build 12-month Point-in-Time (PIT) PD models with SAS & Python.
Develop Lifetime PD models using Cox Proportional Hazard and survival analysis.
Implement IFRS 9 staging rules (Stage 1, 2, 3).
Integrate macroeconomic variables into scenario-based PD forecasting.
Calculate Expected Credit Loss (ECL) under baseline, optimistic, and adverse scenarios.
Validate, monitor, and report IFRS 9 models to meet regulatory standards.

Who this course is for:

Credit Risk Analysts and Risk Modellers who want to build, calibrate, and validate IFRS 9 Probability of Default (PD) and Expected Credit Loss (ECL) models.
Data Scientists and Statisticians seeking practical applications of SAS, Python, and statistical modelling techniques in financial risk management.
Finance and Banking Professionals working in credit risk, loan portfolios, or regulatory reporting who need to understand IFRS 9 requirements.
Actuarial Students and FRM Candidates preparing for professional exams who want real-world modelling examples and case studies.
Credit Risk Modelling who may not have prior experience but are motivated to learn step by step, with code walkthroughs and hands-on examples.

IFRS 9 PIT & Lifetime PD Modelling (SAS, English Course)

What you'll learn

Explore related topics

Course content

Introduction17 lectures • 58min

Data Preparation & Data Quality23 lectures • 1hr 27min

Variable Selection and Model Development28 lectures • 1hr 50min

Model Validation & Perfomance Measurement21 lectures • 1hr 41min

PIT PD Calibration & Forward - Looking Adjustments12 lectures • 53min

IFRS 9 Stagging & Significant Increase in Credit Risk9 lectures • 38min

lifetime PIT PD Modelling17 lectures • 1hr 2min

LGD Modelling using SAS18 lectures • 2hr 40min

Exposure at Default (EAD) Modelling11 lectures • 2hr 7min

ECL Calculation12 lectures • 58min

Requirements

Description

Who this course is for: