Module 1 — AI in Risk Management
- AI-assisted risk scoring
- Early Warning Systems and early risk signals
- Predictive analytics for forward-looking risk assessment
- Anomaly detection and identification of unusual behavior
- AI-assisted risk monitoring and decision support
Module 2 — AI for Fraud Detection
- Transaction and customer behavior analysis
- Detecting unusual transactions and behaviors
- Identifying fraud patterns
- Recognizing new and evolving fraud patterns
- Real-time fraud detection
- Prioritizing AI-generated alerts
Module 3 — AI for AML
- Detecting suspicious transactions and behaviors
- Network analysis for identifying relationships
- Customer risk scoring
- Extracting risk signals from customer and transaction data
- Managing false positives and operational workload
- The potential of AI to support AML investigation processes
Module 4 — AI and Model Risks
- Key components of model risk
- Bias and inaccurate risk assessments
- Explainability of AI-driven decisions
- Impact of data quality on model outputs
- Human oversight and validation of AI results
Case Study — “Design an AI-Powered Fraud Detection System”
Participants design an AI-powered fraud detection solution based on a sample banking fraud scenario.
They define the relevant data and signals, anomalies to be detected, risk-scoring approach, alert mechanisms, false-positive management and required human control points.
By the end of the case study, participants will be able to evaluate AI-based fraud detection systems not only from a technology perspective but also in terms of risk, operations and control mechanisms.