Head of Research Group: Dr . Norbert FOGARASI
Members of the Group: Mohamed Malek AL-FAKIH, Ádám BURGERT, Bence GÉCZI, Péter LANSZKI, Péter MLINKÓ, Mohammed BALAWI, Attila RÁCZ, Artur SAHAKYAN
The Financial AI Research Lab conducts interdisciplinary research at the intersection of computational finance, artificial intelligence, and optimization. Our goal is to develop advanced quantitative methods and intelligent decision-support systems for complex financial problems.
The lab focuses on quantitative financial modeling, machine learning, financial time series analysis, portfolio optimization, algorithmic trading, and predictive analytics. We investigate how data-driven methods and intelligent algorithms can improve investment decisions, risk management, asset pricing, and the operation of modern financial systems. Particular emphasis is placed on intelligent trading systems, adaptive investment strategies, neural-network-based forecasting, and optimization methods for dynamic decision-making under uncertainty.
By combining expertise from finance, computer science, operations research, and data science, the lab bridges theoretical advances and practical applications. Our research aims to develop robust, interpretable, and scalable financial intelligence systems that transform data into actionable insights and support more efficient and informed financial decision-making.
Computational finance is an interdisciplinary engine where algorithms, data-driven intelligence, and financial theory converge to transform market complexity into structured decision-making power
Future research directions, collaboration opportunities
We are open to collaboration opportunities in portfolio optimization, risk management, and algorithmic trading, as well as the development of machine learning and optimization methods for complex financial problems, including participation in national and international research projects.
Key publications
- Racz, A., Fogarasi, N. (2025). Effective Convergence Trading of Sparse, Mean Reverting Portfolios. COMPUTATIONAL ECONOMICS, 66, 2367-2381.
- Racz, A., Fogarasi, N. (2024). Improved Sparse Mean Reverting Portfolio Selection Using Simulated Annealing and Extreme Learning Machine. CONTEMPORARY ECONOMICS, 18(3), 336-351.
- Racz, A., Fogarasi, N. (2022). Trading sparse, mean reverting portfolios using VAR(1) and LSTM prediction. ACTA UNIV. SAPIENTIAE, INFORMATICA, 13(2), 288-302.
