StudentDropoutDataset

This dataset provides comprehensive information on student trajectories and dropout factors at a Spanish technological university specialising in Science, Technology, Engineering, Arts, and Mathematics (STEAM) programmes. It encompasses demographic, socioeconomic, and academic data for all enrolled students across bachelor's, master's, doctoral, and lifelong learning programmes, spanning three complete academic years (excluding pandemic-affected periods). The data were systematically collected from multiple internal sources, standardised, and fully anonymised to ensure privacy compliance.

The dataset comprises 39,364 students, 4,989 courses across 163 degree programmes, and 77 variables capturing diverse dimensions of the student experience, including admission pathways, academic performance indicators, socio-demographic characteristics, digital engagement in the Learning Management System (LMS), and Wi-Fi access patterns. With 464,739 individual records—each representing a course enrolment per student per academic year—the dataset enables robust longitudinal analyses of academic progression and dropout behaviour.

This rich data resource offers significant potential for reuse in multiple research contexts: investigating factors influencing student retention, developing predictive models to identify at-risk students, and conducting comparative studies in higher education settings.