Factors that push students out: a duo studies dropout in higher education
Amanda Emilly Muniz de Menezes and Letícia Karla Soares Rodrigues de Araújo defended at FCTE/UnB an undergraduate thesis identifying academic, demographic and learning factors associated with higher education dropout — and testing predictive models.
Brasília, September 26, 2022
Higher education dropout is one of the costliest indicators for universities and for students themselves — and one of the least observed with enough granularity for coordinated action. This bottleneck is what Amanda Emilly Muniz de Menezes and Letícia Karla Soares Rodrigues de Araújo tackled in their undergraduate thesis, defended in September 2022 at FCTE/UnB under the advising of Prof. Cristiane Soares Ramos and Prof. Sergio Antônio Andrade de Freitas .
The work begins with a systematic literature review to identify which factors — academic, demographic, learning-related — are consistently associated with early student departure. On that foundation, the duo builds predictive models using machine learning algorithms and shows that predictions respond sensitively to changes in course flows: reorganizing curricula, for instance, changes dropout risk for specific cohorts.
The finding matters for Learning Analytics and institutional policy: aligning pedagogical decisions with risk evidence enables targeted interventions — instead of generic campaigns, whose impact is never measured. It is a work that signals a clear direction for universities willing to take data seriously.
The undergraduate thesis is also connected to the paper A Systematic Review of the Factors that Impact the Prediction of Retention and Dropout in Higher Education, published at the 56th Hawaii International Conference on System Sciences in 2023, with Amanda and Letícia among the authors. The paper systematizes the literature behind the work’s predictive stage.
The full text — written in Portuguese — is available at the UnB Undergraduate Theses Digital Library.
About CEDIS: The Center for Studies, Development, and Innovation in Software (CEDIS), linked to the University of Brasília, researches and develops innovative software solutions, with presence in Learning Analytics .