Enhancing supervision with machine learning
About the course
This course will address machine learning for central bankers with a focus on s upervision. Attendees will first learn what ML is, how it works, and its potential use cases across central ban ks, before diving into specific ML use cases for streamlining payment s yste m oversight and banking supervision. The course will discuss the importance of effective data management for central bank supervisory functions, and how ML and AI-enabled tools benefit from digital transformation. After attending, participants will have gained essential knowledge in und erstan ding the application of ML to central bank supervisory technologies.
Tutors
Thomas Gottron
Principal data science expert, data office
European Central Bank
Thomas Gottron is Principal Data Science Expert at the Data Office of the European Central Bank. He leads the activities on Artificial Intelligence, Advanced Analytics and Data Quality to support data science and machine learning projects in all business areas. Furthermore, he coordinates the ECB Machine Learning Community, which serves as platform to transfer knowledge and experience across more than 900 colleagues from all business areas at the ECB and other central banks.
Mr. Gottron has a background in mathematics and business management and received a PhD in computing science in 2008. He has more than 20 years of experience in designing and implementing data driven projects in academics, in the private and in the public sector. He authored more than 100 scientific publications on topics related to information retrieval, artificial intelligence, and data integration. His academic work has received several prices, including the Internet technologies and Applications best paper award 2009, winner of the Semantic Web Billion Triple Challenge in 2011 and the Web Science Test of Time Award 2026 as recognition for a paper that has stood the test of time through continued relevance and impact.
Agenda
Introduction to machine learning for central banks
- Defining machine learning (ML) as a subset of AI
- Role of ML in sourcing and processing increasingly large and complex data
- How are central banks deploying ML across a variety of use cases?
- Essential ML techniques: supervised, unsupervised, and reinforcement learning
Role of ML and AI within the suptech landscape
- Importance of data access and management for central bank supervisory functions
- Digital transformation and the role of the cloud
- Risks and benefits associated with ML and AI-enabled supervision
- Overview of current ML and AI-powered sup tech tools across global central banks
Oversight of payment systems with ML
- Utilizing ML to identify anomalous payment transactions
- Comparison of efficiency and effectiveness between ML models and traditional methods of payment oversight
- Balancing accuracy with explainability: assessing the results ML algorithms
Leveraging ML for efficient banking supervision
- Strengthening data quality with ML for improved information flows between supervisors and the entities they oversee
- ML-enabled anomaly detection in data reported by financial institution s
- Text analysis for supervisors: d ocument classification, sentiment analysis, and risk monitoring
Learning objectives
- Build an understanding of ML infrastructure and techniques
- Learn how ML can be applied across central bank operations
- Understand the importance of data management for supervisory functions
- Explore how ML can improve payment systems overnight
- Identify the potential role of ML in efficient banking supervision
Who should attend
Relevant titles and departments may include, but are not limited to:
- Supervision departments
- Heads of supervision
- Banking supervisors
- Stress testing analysts
- Risk inspectors
- Suptech developers/analysts
- Data departments
- Chief data/AI officers
- Heads of innovation
- Digital transformation leads
- Data analysts
- ML engineers
- IT departments
- Heads of information technology
- IT analysts
