Education inequalities persist globally, particularly in Italy, often influenced by factors beyond student ability. This paper aims to study the pure territory effect on education inequalities controlling for other factors such as gender, socioeconomic status, and high school performance. As in a clinical study, we evaluate the effect of multiple treatments represented by territorial clusters on the students’ enrolment choices. The inverse of propensity score estimates obtained with a gradient-boosted model (GBM) procedure are used as weights of a multinomial logistic regression model to evaluate the probability of enrolling at the university inside or outside their own place of residence. The study highlights the importance of considering the complex interplay between territory and economic variables in explaining inequalities in the transition from high school to university. Especially in northern regions, we show that the territorial effect on mobility choices, was covered by socioeconomic status and previous educational attainment. In the southern regions, the results highlight a more pronounced territorial heterogeneity regarding the choice to move to another region compared to northern regions.

Students’ and graduates’ mobility is an interesting topic of discussion especially for the Italian education system and universities. The main reasons for migration and for the so called brain drain, can be found in the socio-economic context and in the famous North–South divide. Measuring mobility and understanding its dynamic over time and space are not trivial tasks. Most of the studies in the related literature focus on the determinants of such phenomenon, in this paper, instead, combining tools coming from graph theory and Topological Data Analysis we propose a new measure for the attitude to mobility. Each mobility trajectory is represented by a graph and the importance of the features constituting the graph are evaluated over time using persistence diagrams. The attitude to mobility of the students is then ranked computing the distance between the individual persistence diagram and the theoretical persistence diagram of the stayer student. The new approach is used for evaluating the mobility of the students that in 2008 enrolled in an Italian university. The relation between attitude to mobility and the main socio-demographic variables is investigated.