Ioannis Anagnostou is based at ING Groep N.V. 2016-2019, and his research project is Machine Learning Algorithms for Risk Management in Trading Activities (WP4)
“BigDataFinance brings together researchers from across the world with diverse academic and professional profiles, passionate about applying data-driven techniques to real problems of the financial industry”
I joined the Quantitative Analytics team of ING Financial Markets and the Computational Science Lab of the University of Amsterdam (UvA) in June 2016 to work on developing a prototype framework for pricing and risk management using machine learning algorithms, as part of BigDataFinance 2015-2019. Previously, I worked for 3 years at the Royal Bank of Scotland as a Senior Analyst within the Risk Analytics and Models team, where I focused on the development of credit risk grading models, Economic Capital modelling, and Stress Testing of a range of portfolios of RBS. This involved performing sophisticated data manipulation, classification and regression techniques, Monte Carlo simulations, as well as econometric time-series modelling using macroeconomic variables.
I hold a double MSc in Financial Mathematics with Distinction from the University of Edinburgh and Heriot-Watt University, and a BSc & MSc in Applied Mathematics from the National Technical University of Athens. During my MSc in Edinburgh, I researched Contagious Defaults at Scottish Widows Investment Partnership (SWIP), one of Europe’s largest Asset Management companies (now part of Aberdeen Asset Management). Prior to that, in Athens, I conducted my thesis research on option pricing under exponential Levy models, and interned with Athens Stock Exchange and the Hellenic-American Education Foundation.
The opportunity to apply and expand my knowledge, and engage more deeply with issues that inspired me so far in my career, motivated me to apply for the BigDataFinance project. BigDataFinance brings together researchers from across the world with diverse academic and professional profiles, passionate about applying data-driven techniques to real problems of the financial industry. There are numerous possibilities to travel and collaborate with international research teams specializing in machine learning, complex networks, and high-frequency econometrics, as well as with leading private sector partners. The opportunity to do this while being based in a bank that invests heavily in innovation, and in an academic group of experts in complex systems research at the same time, made the project extremely attractive to me. I am sure that BigDataFinance will contribute enormously to my academic, professional and personal advancement.