Mathematical Finance & Financial Data Science Seminar
Complexity and Machine Learning with Applications to Markets
Speaker: Nino Antulov-Fantulin, senior researcher at ETH Zurich
Location: Online
Date: Tuesday, May 11, 2021, 5:30 p.m.
Synopsis:
Complexity science studies systems and problems that are composed of many components that may interact with each other in a dynamic and non-linear way. In this talk, the author will address several research questions and directions at the interface of complexity and machine learning with applications to financial markets.
(i) How can complexity science give insights about financial systems? In this part, the author will present some of the complexity concepts like cohesiveness, transfer entropy and its relation to volatility and returns.
(ii) Machine learning models in Cryptocurrency markets. Here, the author will present the class of mixture models for inferring the short-term volatility of Bitcoin.
(iii) Neural-Network Control of Dynamical Systems.
Finally, the author presents the ability of neural networks to steer or control trajectories of dynamical systems, coupled with graphs.
Speaker Bio
Nino is a senior researcher at ETH Zurich, where he works at the interface of complexity and data science. His main interests include complex systems, predictive analytics in finance, machine learning, social network analysis and Monte-Carlo algorithms. He is also a visiting researcher at Courant Institute of Mathematical Sciences, supervisor & panel member of PhD Program in Data Science at Scuola Normale Superiore and head of research at Aisot GmbH, Zurich. Prior to ETH Zurich, he worked at the Rudjer Boskovic Institute and Faculty of Electrical Engineering and Computing, Croatia and he was a visiting scientist at Robert Koch Institute, Berlin. He worked on several EU projects with emphasis on complex systems: (i) FOC−“Forecasting Financial Crisis”, (ii) Multiplex−“Foundational Research on MULTI-level comPLEX networks and systems and data science EU projects: (iii) SoBigData - "Social Mining & Big Data Ecosystem", and (iv) e-Lico− “An e-Laboratory for Interdisciplinary Collaborative Research in Data Mining and Data-Intensive Science”.
Notes:
This event is free, but requires registration. Please click here to register.