Agenda
Agenda
Training Agenda
Data analytics for AML/CFT: AI and Machine Learning in focus
Pre-recorded presentation
- State of the art in AI and Machine Learning
- Key opportunities for AML and CFT
- Implications for data management, processing and analysis
- Examples of Machine Learning based software solutions for the regulators and the regulated
Kimmo Soramäki is the founder and CEO of Financial Network Analytics (FNA) and the founding editor-in-chief of The Journal of Network Theory in Finance. He started his career as an economist at the Bank of Finland where he developed in 1997 the first simulation model for interbank payment systems. In 2004 while at the research department of the Federal Reserve Bank of New York, Mr Soramäki was among the first to apply methods from network theory to improve our understanding of financial systems. During the financial crisis of 2007-2008 he advised several central banks, including the Bank of England and European Central Bank, in modelling interconnections and systemic risk. This work led him to found FNA in 2013 provide solutions to monitor the complex financial networks that play a continually larger role in the world around us. Mr Soramäki holds a Doctor of Science in Operations Research and a Master of Science in Economics (Finance), both from Aalto University in Helsinki.
New opportunities in AML, CFT and Anti-fraud
Pre-recorded presentation
- Key financial crime risks of the digital era
- Examples of Big Data and Machine Learning applications in KYC and KYCC
- The role of international and public-private cooperation and coordination
- Automated vs manual Fraud and AML investigation
Building Blocks of Network Analytics
11:00 – 12:00
Exposure Networks and Stress Testing
-
Focus on the practical application of network analytics in measuring, mapping and modelling of financial exposures
-
Network analysis of trade repository data and identification of systemically important financial institutions
-
Understanding complex instruments that may hide substantial risks - as highlighted by the agent-based models in the Financial Crisis
-
Hands-on use of interactive dashboards in relation to Case Studies of e.g. CBMX index, Bank for International Settlement's bank's country risk exposure
12:00 – 12:15
Break
12:15 – 13:15
Correlation Maps: A Systemic View of Financial Markets
-
Presentation of advanced correlation maps visualising interconnectivity of markets
-
Focus on Value at Risk analytics and outlier detection
-
Development of early warning signals through monitoring of interconnected market dynamics and visual
-
Statistical identification of hidden patterns in complex data
-
Hands-on use of dashboards for Case Studies (e.g. US Housing Bubble and Crisis)
13:15 – 13:30
Break
13:30 – 14:30
Stress Testing Correlation Networks
-
Focus on financial markets as a complex system with numerous measurable interdependencies
-
Production of 'what if' scenarios to predict movements of markets under stress
-
Stress testing correlation structures
-
Hands-on use of interactive dashboards in relation to Case Studies (e.g. Brexit Referendum and US Presidential Election)
Practical Applications: Understanding, Visualising and Managing Risks
11:00 – 12:00
Using Network Simulations to Design FMIs
-
Modelling FMIs as complex systems with 'Agent-Based Modelling'
-
Measuring liquidity efficiency
-
Developing new Liquidity-Saving Mechanisms
-
Hands-on use of interactive dashboards in relation to Case Studies (e.g. CLS, LVTS, CHAPS)
12:00 – 12:15
Break
12:15 – 13:15
Monitoring and Stress Testing FMIs and their Members for Liquidity, Solvency and Systemic Risk
-
Using payment data to measure liquidity and solvency of financial institutions
-
Real-time monitoring and outlier detection
-
Developing stress scenarios (participant failure, operational issues, etc.)
-
Using Agent-Based Simulations to evaluate different stress scenarios
-
Running simulations
-
Hands-on creation and analysis of transaction networks (e.g. from Trade repository or payments data)
13:15 – 13:30
Break
13:30 – 14:30
Diagnostic Analytics: Detection and Investigation of Financial Crime and Cyber Attacks
-
Improving fraud detection and AML with network theory
-
"Following the money" and automating the manual investigation of financial crime
-
Identification of DDoS attack patterns through real-time detection of anomalies in cyber networks
-
Cyber attacks and technological and infrastructure interdependencies
-
Hands-on use of interactive dashboards in relation to Case Studies
-
Hands-on creation and analysis of related party networks