Many educational institutions are using predictive models to leverage actionable insights using student data and drive student success. A common task has been predicting students at risk of dropping out for the necessary interventions to be made. However, issues of discrimination by these predictive models based on protected attributes of students…

Tackling early leaving from education and training (ELET) is one of the headline targets for education policy in the European Union. Although ELET rates have been decreasing in most member states, male, socially disadvantaged and immigrant students remain overrepresented in ELET figures. Moreover, students in vocational tracks and students who…

We perform two approaches of machine learning, logistic regressions and decision trees, to predict student dropout at the Karlsruhe Institute of Technology (KIT). The models are computed on the basis of examination data, i.e. data available at all universities without the need of specific collection. Therefore, we propose a methodical approach…

Identities extend standard models that explain student motivations to complete courses at technical college. A differential hypothesis was that profiles of identities (individuality, belonging and place) explain the self-concepts and task values that contribute to participation, considering demographic factors (age, gender, location, paid work).…