Objective:
Understand predictive modeling techniques for fraud risk detection.
- Develop predictive models to identify fraud-prone behaviours and high-risk transactions.
- Apply AI and big data analytics to anticipate fraudulent activities.
- Strengthen fraud prevention strategies with global compliance frameworks.
- Align fraud risk management with ISO 37001, ACFE, and AML principles.
- Build resilient systems for proactive fraud prevention.
Content:
Introduction to Financial Fraud & Analytics
- Types of Fraud
- Evolution of Detection
- Fraud Detection Frameworks
Data Preparation and Feature Engineering
- Data Aggregation
- Data Preprocessing
- Feature Engineering
- Addressing Imbalanced Data
Predictive Modeling Techniques (Supervised Learning)
- Classification Models
- Deep Learning
- Ensemble Methods
Anomaly Detection (Unsupervised Learning)
- Anomaly Detection Algorithms
- Pattern Recognition
Model Evaluation and Interpretation
- Metrics for Evaluation
- Explainable AI (XAI)
- Positive Unlabeled Learning (PUL)
Implementation, Deployment, and Strategy
- Real-time Monitoring
- Operationalizing Models
- Continuous Learning
For Whom:
- Financial Directors
- Senior Executives in the Finance sector
- Chief Financial Officer
- Finance Managers
- Chief Risk Officers
- Risk Managers
- Internal Auditors
- Professionals reporting to the CFO and CRO