Bio: Paolo Barucca is Associate Professor at UCL Computer Science. He obtained his PhD in Theoretical Physics from Sapienza University of Rome. He works on Statistical Physics of Complex Systems, Statistical and Machine Learning in Finance and Economics. He collaborates with private and public institutions for teaching and research activities on machine learning and statistical data science in finance and economics applied to risk assessment and predictive modeling.Google Scholar.

https://paolobarucca.com/

Title: Modelling financial markets: from network theory to machine learning

Abstract: The number of financial transactions happening every second is ever-increasing, occurring on a variety of marketplaces, performed by different market players, and related to more and more interdependent complex instruments.

Monitoring financial markets requires making sense of multiple data structures and data sources, describing our societies and economies, not only our markets. Stochastic modeling remains a fundamental benchmark, but complex market behaviors require data-driven modeling hardly captured by standard theory.

Network theory is a powerful framework for modeling dynamic multi-layered relationships between financial institutions and for training non-linear multivariate models -including machine learning ones- needed to capture the complex interdependencies of financial variables and to provide timely and informative indicators about the financial system.