Check also:
Mini Track Chair:
The integration of data science into behavioral economics has created new opportunities for analyzing and understanding human decision-making. Behavioral economics has reshaped traditional economic thinking by emphasizing cognitive biases, bounded rationality, and social influences that drive individual and collective choices. At the same time, advances in data science and machine learning provide powerful tools to collect, process, and interpret increasingly large and complex datasets, ranging from online surveys and controlled experiments to digital traces of real-world behavior.
This mini-track seeks to highlight how these two fields can be combined to improve our understanding of decision-making processes and to inform evidence-based policy and business strategies. Data science methods such as machine learning, natural language processing, and predictive analytics allow researchers and practitioners to uncover patterns in both individual behavior (such as overconfidence, the ability to delay of gratification, or heterogeneous risk preferences) and aggregate behavior, including market sentiment, bubbles formation and crashes, as well as collective responses to uncertainty.
We encourage submissions that explore methodological, empirical, and experimental approaches to behavioral economics using data science. Topics of interest include, but are not limited to: applications of machine learning to behavioral datasets, cognitive biases in financial and consumer decisions, modeling aggregate economic decisions, market sentiment and stock market dynamics, bubble formation and crashes, and the use of neuroscience or biometric experiments to analyze or predict individual and group decisions
Topics of interest include, but are not limited to:
Mihai Toma is a Lecturer at the Bucharest University of Economic Studies, Faculty of Business Administration in Foreign Languages (FABIZ), where he teaches topics such as Economics of Information, AI Strategy and Digital Transformation or Decision-making for Business using ML.
He brings over a decade of combined academic and industry experience, with expertise spanning financial markets, behavioral finance, AI, and neurofinance. Mihai developed and conducted the first series of neurofinance experiments in Romania in 2017, pioneering the integration of neural and biometric data into financial decision-making research.
Alongside his academic career, Mihai is currently a Model Manager at the London Stock Exchange Group, applying advanced quantitative methods to sustainable finance models. His professional background also includes roles as a financial engineer at Finastra and as an economist in the Financial Stability Department of the National Bank of Romania.
Mihai holds a PhD in Finance (2018) and was a Fulbright Scholar and postdoctoral researcher at the California Institute of Technology (Caltech), where he spent 2.5 years conducting research at the intersection of finance, technology, and neuroscience.
