For the high-flex option, register in advance. You will receive a confirmation email containing information about joining the meeting.

Title:
How Can Data Science Assist Decision-Making in Higher Education?

Abstract
Educational data science is a rapidly evolving field that aims to extract actionable knowledge from large-scale educational data using statistical and machine learning methods. In this overview talk, I present data-driven approaches that support evidence-based decision-making in higher education by leveraging administrative and academic datasets. I discuss my team's research on identifying students at risk of dropping out, assessing the predictive validity of admission systems, uncovering key determinants of student success, and analyzing the relationship between student evaluations of teaching and grade inflation. I also briefly address the role of explainable artificial intelligence (XAI) in increasing transparency and trust in educational analytics. Finally, I introduce a deployed web-based decision-support application that uses predictive and interpretable machine learning techniques to assist prospective students in making more informed academic choices.

Bio:
Dr. Roland Molontay is an applied mathematician, data scientist, and network scientist. He is an Associate Professor at the Budapest University of Technology and Economics (BME), Deputy Director of the BME Institute of Mathematics, and Head of the Human and Social Data Science Lab. He also serves as Head of the Institute of Biostatistics and Network Science at Semmelweis University and leads the Research Abroad Program at the Aquincum Institute of Technology (AIT-Budapest). His research focuses on educational data science, network science, and interpretable machine learning, with particular emphasis on socially relevant large-scale data. He investigates both foundational and applied aspects of data science, aiming to develop computational tools that support evidence-based decision-making in higher education and beyond. He has led numerous national and international research projects and R&D collaborations with industry partners. Dr. Molontay has authored over 40 peer-reviewed publications, and his work has appeared in leading journals such as Nature Communications and the International Journal of Artificial Intelligence in Education. He has received multiple prestigious awards for his research and teaching. He is passionate about leveraging data science to improve higher education outcomes and strengthen the research–education interface.

Citation:
Nagy, M., & Molontay, R. (2024). Interpretable dropout prediction: Towards XAI-based personalized intervention. International Journal of Artificial Intelligence in Education, 34(2), 274-300. https://link.springer.com/article/10.1007/s40593-023-00331-8