AI for Fraud Detection & Anti‑Money Laundering Training Course

Introduction to AI in Financial Crime

• Overview of fraud and AML challenges in the era of digital finance.
• Comparative analysis of traditional versus AI-driven approaches.
• Real-world case studies from Mastercard, JPMorgan, and other global banks.

Machine Learning for Transaction Monitoring

• Applying supervised learning for risk scoring and classification.
• Utilising unsupervised learning techniques for anomaly detection.
• Implementing real-time alert generation and stream processing.

Graph Analytics and Network Risk Detection

• Modelling the relationships between entities and transactions.
• Identifying complex fraud schemes using graph AI.
• Practical sessions with Neo4j or comparable tools.

Natural Language Processing for AML

• Text mining techniques for customer due diligence (CDD).
• Watchlist scanning using named entity recognition (NER).
• Prompt-based document review and the creation of suspicious activity reports (SARs).

Model Governance and Explainability

• Constructing models that are both explainable and auditable.
• Detecting and mitigating bias within fraud detection algorithms.
• Applying XAI techniques in compliance contexts.

Ethics, Regulation, and Model Risk

• Ensuring compliance with AML and KYC frameworks (e.g., FATF, FinCEN, EBA).
• Navigating AI ethics in surveillance and customer monitoring.
• Upholding reporting standards and ensuring regulatory auditability.

Deployment Strategies and Future Trends

• Integrating AI models into existing transaction systems.
• Establishing feedback loops and model updating mechanisms.
• Exploring the role of generative AI in fraud investigation and SAR automation.

Summary and Next Steps