Identifying Students at Risk to Academic Dropout in Higher Education

Abstract

A main goal of the university institution should be to reduce the desertion of its students, in fact, the dropout rate constitutes a basic indicator in the accreditation processes of university centers. Thus, evaluating the cognitive functions and learning skills of students with an increased risk of academic failure can be useful for the adoption of strategies for preventing and reducing school dropout. In this research, cognitive functions and learning skills in 284 university students were evaluated. Academic performance predictors were identified, and conglomerates analysis was carried out to establish groups according to those variables. The stability and validity of the conglomerates were tested with discriminant analyzes and comparison tests. The variables associated significantly to academic performance were: attention, intelligence, motivation, metacognition and affective components. The conglomerate analysis suggested a three-group solution: (1) students with cognitive skills of moderate to high, but deficient learning strategies; (2) students with cognitive and learning capabilities of moderate to high; (3) students with cognitive functions low and moderate learning capacity. Students from groups 1 and 3 showed worse academic performance; 83.3% of students at risk of desertion belonged to such groups. Two groups of students have been identified with the highest risk of academic failure: those with poor cognitive capacity and those with bad learning skills.

Factores asociados a la deserción estudiantil en el ámbito universitario. Una revisión sistemática 2018-2023

“…En este sentido, si el éxito es escaso, el desempeño decae y la deserción se convierte en una opción. Asimismo, según lo señalado por Gómez et al (2021), los estudiantes con mayor riesgo de fracaso académico y, por consiguiente, de deserción, son aquellos que muestran un bajo nivel cognitivo y carecen de aptitudes para un aprendizaje eficaz.…”

“…Los estudiantes con mayor riesgo de fracaso académico, y, por consiguiente, de deserción, son los que muestran bajo nivel cognitivo además de carecer de aptitudes para un aprendizaje eficaz (Gómez et al, 2021).…”

“…Actualmente, el fenómeno de la deserción universitaria constituye una problemática que involucra a la sociedad en su conjunto, ya que tiene un impacto significativo en la disminución del aporte intelectual y el potencial aumento de la pobreza (Parra et al, 2023). Esta situación es influenciada por factores como los contextos educativos, las condiciones socioeconómicas en las que viven los estudiantes (Chalpartar et al, 2022;Himmel, 2002) y últimamente ha sido exacerbada por la pandemia del covid-19, aunque viene ocurriendo desde hace décadas en distintas partes del mundo, de ahí que haya captado la atención de gobiernos, autoridades académicas y la sociedad en general (Gómez et al, 2021).…”

The Role of Career Adaptability and Academic Engagement in College Student’s Life Satisfaction

“…Empirical studies [37][38][39] and an integrative review [39] considering higher education students from European, North, and South American contexts have similarly suggested that engagement in academic activities is positively linked to academic achievement and adjustment. On the other hand, students who participate less frequently in class and academic tasks tend to demonstrate a higher risk of dropout [40][41][42]. Thus, academic engagement is an important factor that prevents dropout and academic failure not only in high school [40] but also in higher education [6,42].…”

Comparison of Predictive Models with Balanced Classes Using the SMOTE Method for the Forecast of Student Dropout in Higher Education

“…Although we focused our analysis on work that applied machine learning and EDM techniques to predict student dropout, other techniques have been investigated for the detection and adoption of strategies for preventing and reducing student dropout. For instance, evaluating the cognitive functions and learning skills of students [34], using non-linear panel data models to analyze the determinants of student dropout [35], or applying learning analytics to identify students at risk of dropout [36].…”