Academic dropout remains a significant challenge for education systems, necessitating rigorous analysis and targeted interventions. This study employs machine learning techniques, specifically random forest (RF) and feature tokenizer transformer (FTT), to predict academic attrition. Utilizing a comprehensive dataset of over 40 000 students from an…

Many of the first-year undergraduate students who enrol in universities, particularly in top-ranked private universities in Bangladesh, struggle with getting good grades. As a result, many students look forward to a bleak future, dropping out midway through their studies. Thus, improving the rates of graduation and reducing the rates of attrition…

The expansion of the higher education sector in Australia opened up new pathways into university increasing the diversity of the student population. For non-traditional students, those who did not successfully complete secondary school, barriers to gaining entry into university have been dismantled, however, previous research suggests that…

The literature suggests that student attrition at the university level has been of growing concern in many countries. Student attrition has a number of implications for universities, chief amongst them are losses to revenue and investment in higher education. While many studies have examined causes for attrition from an institutional perspective,…

Attrition from Canadian graduate programs is a point of concern on a societal, institutional, and individual level. To improve retention in graduate school, a better understanding of what leads to withdrawal needs to be reached. This paper uses logistic regression and discrete-time survival analysis with time-varying covariates to analyze data…

This paper describes results from a case study that focuses on the initial implementation of a new, online instructional program, the WebIT M.S. in Instructional Technology, offered at the University of Tennessee at Knoxville during 2008-2010. Survey data were collected from two groups of students: a self-selected sample of those students who…

The main aim of this study was to gain a better understanding of why students abandon their studies, or perform less well than expected given their high school grades, and to develop predictive models that can help identify those students most at-risk at the time they enter college. This will allow teachers and those responsible for student…

The relationship between student dropout and high school grades, demographic factors and psychosocial variables was examined for 40 682 full-time Dawson College students. Overall, low high school grades and older age were the best predictors of dropout. Male students, who generally had lower grades than females, were more likely to drop out than…

We use data from the 1990/1994 Beginning Post-Secondary Survey to determine whether the factors associated with long-term attrition from higher education differ for students who initially enrolled part-time as compared to for students who initially enrolled full-time. Using a two-stage sequential decision model to analyze the initial enrollment…

Data from the National Longitudinal Study of the High School Class of 1972 indicate that women are more likely to withdraw only in two year colleges and that whites are more likely to withdraw than blacks. High school program, college grades, and educational aspiration are significantly related to withdrawal, but receipt of financial aid is not.…

All first-year students enrolled in diploma and certificate programs in the Saskatchewan Institute of Applied Science and Technology (SIAST) were surveyed to determine factors that influence student persistence. A questionnaire was mailed to 2,822 students in October 1991; 1,557 completed questionnaires were received and analyzed. A follow-up…

Reports on a study of the effects of seven preenrollment characteristics (i.e., ability, socioeconomic status, race, sex, high school program, high school grades, and educational aspirations) and three student-institutional characteristics (i.e., entry status, full/part-time status, and curriculum type) on student retention in college. Looks at…

This survey of a national sample of 451 deaf adolescents found that many factors predicting attrition in general education also apply to deaf education. These include individual ability, local educational values, and demographic traits. Regional differences were also found, with programs in the southeast and southwest losing more students than…

Presents a research-based model of student persistence. Concludes that high school academic achievement, needs for financial aid and employment, day/evening status, goal commitment, and expected student/college fit have primary effects on persistence, while background characteristics and academic self-confidence have secondary effects. Explains…

In Spring 1980, a study was conducted at Mercer County Community College (MCCC) to determine selected information about students who indicated during Fall semester registration that they intended to return the following Spring, but who failed to do so. One aspect of the study involved a comparison of returning and non-returning students with…