Using machine learning to model interaction effects in education : a graphical approach

authors: Fritz Schiltz (researcher, Leuven Economics of Education Research, University of Leuven, Belgium), Chiara Masci (PhD student, Modelling and Scientific Computing, Department of Mathematics, Politecnico di Milano, Italy), Tommaso Agasisti (associate professor, Department of Management, Economics and Industrial Engineering, Politecnico di Milano, Italy), Daniel Horn (senior research fellow, Centre for Economic and Regional Studies, Hungarian Academy of Sciences, Hungary)

Educational systems can be characterized by a complex structure: students, classes and teachers, schools and principals, and providers of education. The added value of schools is likely influenced by all these levels and, especially, by interactions between them. We illustrate the ability of Machine Learning (ML) methods (Regression Trees, Random Forests and Boosting) to model this complex 'education production function' using Hungarian data. We find that, in contrast to ML methods, classical regression approaches fail to identify relevant nonlinear interactions such as the role of school principals to accommodate district size policies. We visualize nonlinear interaction effects in a way that can be easily interpreted.

MoreLess

Alternative title:	Gépi tanulás használata az interakciós hatások modellezésére az oktatásban : egy grafikus megközelítés
Year of publication:	June 2017
Authors:	Schiltz, Fritz ; Masci, Chiara ; Agasisti, Tommaso ; Horn, Dániel
Publisher:	Budapest : Institute of Economics, Centre for Economic and Regional Studies, Hungarian Academy of Sciences, Department of Human Resources
Subject:	machine learning \| education production function \| interaction effects \| non-linear effects \| Lernprozess \| Learning process \| Lernen \| Learning \| USA \| United States \| Theorie \| Theory \| Bildungsertrag \| Returns to education