Aarhus University Seal / Aarhus Universitets segl

Martin Magris


Martin Magris


Short Bio
Since October 2020, Martin Magris is a postdoctoral researcher at the Department of Engineering at Aarhus University (Denmark), funded by the EU-IF grant BNNmetrics. His research interest span across high-frequency econometrics and machine learning applications in finance. He completed his Ph.D. in econometrics in 2019 at Faculty of Information and Communication Technology, Tampere University (Finland), within the Marie Curie BigDataFinance training network. He received his B.Sc. in Statistics and Mathematics in 2013 and his M.Sc. in Statistical and Actuarial Sciences in 2015 from University of Trieste (Italy). Before commencing his postgraduate studies, Martin worked as a non-life actuarial analyst, pricing, developing and back-testing car-insurance and multiple-peril insurance products.
About the Project
My name is Martin Magris, post-doctoral researcher at Aarhus University. I joined the Machine Learning and Computational Intelligence group (MaLeCi) at the Section of Electrical and Computer Engineering, Aarhus University (Denmark), on fall 2020 with the EU-funded project BNNmetrics.
The aim of my research is to explore the applicability of Machine Learning (ML) as a successful tool for econometrics and finance. In particular my current research focus in on a sub-class of Deep Learning algorithms knows as Bayesian Neural Networks which is particularly attractive since embedding the desirable and robust probabilistic properties typical of econometric modelling and the great flexibility typical of ML algorithms. The challenges towards this research direction are manifolded across modern (bayesian) statistics, state-of-the art ML methodologies, high-frequency econometrics modelling and the ubiquitous big-data issues underlying all the empirical analyses.
With this spirit, my research aims at showing how to best exploit the methods, models, and approaches from these two domains for tacking complex, multi-layered and high-dimensional problems that characterize modern financial markets. I am working on developing models and exploring different solutions for a variety of classification and prediction problems from both a theoretical and applied perspective, with an eye on the needs of the financial industry as well.
Horizon 2020 Call: H2020-MSCA-IF-2019 (Marie Skłodowska-Curie Individual Fellowships)
Topic: MSCA-IF-2019
Type of action: MSCA-IF-EF-ST (Standard European Fellowships)
Granted by: Research Executive Agency
Grant agreement number: 890690
Acronym: BNNmetrics
Funding period: October 1st, 2020 - August 30th, 2022 (24 months)

Vis alle (7) »

Vis alle (16) »

Vis alle (3) »

ID: 197417621