Objective

Machine learning methods currently rank among the most powerful and rapidly evolving developments in the financial sector. This course explores various advanced machine learning techniques and highlights their relationship with conventional statistical methods.

This course also addresses the practical challenges associated with the adoption of machine learning by central banks. It provides a forum for central bankers, regulators, and supervisors to discuss strategies for implementing machine learning models, thereby facilitating the exchange of knowledge across countries on this increasingly important topic. 

Contents

• Interpretable Machine Learning
• Causal Inference
• Natural Language Processing

Participants will have the opportunity to discuss questions about machine learning methods and their practical implementation using provided sample codes in Python. Participants are expected to make active contributions to the discussions, including sharing their previous experiences, lessons-learned, and current challenges related to the implementation of machine learning in their own jurisdiction.

Target group

The course is aimed at data-savvy central bankers, regulators and supervisors in areas such as information technology and statistics, or research departments interested in implementing advanced machine learning methods.

Previous knowledge of data analysis (including linear and logistic regression) and statistical software (including base commands in Python) is required.

Technical requirements

Computer with microphone, camera, speakers or headphones; an up-to-date internet browser; working Python installation.