Description
Description
This training dives deep into the statistical and analytical aspects of credit risk modeling. It covers advanced modeling techniques, the complete model development and validation process, and the application of machine learning and AI in risk assessment.
Target Audience:
Data scientists, risk modelers, quantitative analysts, and other technical professionals
Course Outline
- Credit Scoring
- Credit Risk Model Lifecycle
- Technology and Infrastructures Needed
- Software and Tools
- Coding Low-Code Platforms
- Credit Risk Modeling for Basel & IFRS 9
- Basel Accords: I, II, III, and IV
- Basel Approaches
- Merton Model
- Risk Weight Functions
- Feature Engineering
- RFM Features
- Trends and Ratios
- Transformations
- Principal Component Analysis
- Thermometer Coding
- Variable Selection
- Filter Methods
- Automated Methods
- Backward Regression Trimming
- Estimation Techniques
- Multivariate Analysis
- Regression techniques
- Decision Trees
- Ensemble Models: Bootstrapping, Random Forests, XGBoost
- Hyperparameter Optimization
- Low-Default Portfolio
- Modeling Approaches
- Shadow Rating
- Under sampling / Oversampling
- SMOTE approach
- Adjusting Posterior Probabilities
- Calibration Approaches
- Model Assessment Methods
- Cross-validation
- Data Partition Method
- Confusion Matrix
- Performance metrics: ROC and AUC, Lift Curve, Gini, Accuracy Ratio, KS
- Performance Baselines
- Other Topics
- Role of GenAI
- Role of Alternative Data
- Credit Scoring Case Studies
- Credit Scoring for SMEs
- Credit Scoring for Consumer Loans
- Risk and Challenges
- Implementation Challenges
- Bias and Interpretability
- Computation Costs
RESOURCE SPEAKER:
Mr. Ricardo Ian P. Copia
Training Consultant
SCHEDULE:
April 21 – 22, 2026 (Tuesday-Wednesday) 9:00 AM – 5:00 PM
Training Fee Per Participant:
Member Institution – Php7,840.00
Non-Member Institution – Php10,080.00
*VAT inclusive