AI for Fraud Detection & Anti‑Money Laundering Training Course

Introduction to AI in Financial Crime

• Perspectives on fraud and AML challenges in the digital finance landscape
• Comparing traditional methods with AI-driven approaches
• Real-world case studies involving Mastercard, JPMorgan, and global banking institutions

Machine Learning for Transaction Monitoring

• Applying supervised learning for risk scoring and classification tasks
• Utilizing unsupervised learning techniques for identifying anomalies
• Generating real-time alerts and managing stream processing

Graph Analytics and Network Risk Detection

• Modeling connections between various entities and transactions
• Identifying sophisticated fraud schemes through graph AI
• Practical exercises using Neo4j or comparable tools

Natural Language Processing for AML

• Applying text mining to customer due diligence (CDD) processes
• Enhancing watchlist scanning via named entity recognition (NER)
• Using prompt-based methods for document review and suspicious activity reports (SARs)

Model Governance and Explainability

• Constructing models that are both explainable and auditable
• Identifying and mitigating bias within fraud detection algorithms
• Implementing XAI techniques to meet compliance requirements

Ethics, Regulation, and Model Risk

• Aligning with AML and KYC frameworks such as FATF, FinCEN, and EBA
• Navigating AI ethics in surveillance and customer monitoring practices
• Meeting reporting standards and ensuring regulatory auditability

Deployment Strategies and Future Trends

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

Summary and Next Steps