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…

Background/Context: There is a misalignment in contemporary society between the assumption that all high school graduates can and should attend college and the lack of funding and support to make that happen. This is especially apparent at community colleges that enroll disproportionally low-income students, who deal with a variety of obstacles…

Purpose: This study aimed to use enrollment information including demographic, family background and financial status, which can be gathered before the first semester starts, to construct early prediction models (EPMs) and extract crucial factors associated with first-year student dropout probability. Design/methodology/approach: The real-world…

This paper combines a theoretical-based model with a data-driven approach to develop an Early Warning System that detects students who are more likely to dropout. The model uses innovative multilevel statistical and machine learning methods. The paper demonstrates the validity of the approach by applying it to administrative data from a leading…

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…

Degree transfer is understood as the increasingly common phenomenon among students of changing university degrees or university, especially after the first or second years of the degree. The profile of students who transfer (3,861students, 8.3% of students) is constructed based on microdata from the University Pre-enrolment Register of Catalonia…

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…

Despite a diverse body of literature on college student retention, studies focusing on small, private, selective liberal arts colleges are limited. This study utilized a mixed methodology beginning with logistic regression analyses and followed with a qualitative inquiry that included interviews with students who had not persisted. While variables…

Actual school dropout among immigrant youth has been addressed in a number of studies, but research on hidden school dropout among immigrant students is rare. Thus, the objective of this paper is to analyze hidden school dropout among primary school students with an immigrant background. The analyses were performed using survey data of 1186…

It is estimated that of approximately 150-250 million children with disabilities across the world, a large number have difficulties related to problems in the central nervous system (CNS). This paper considers school dropout rates of children with special educational needs associated with CNS problems from a study of educational institutions in…

This study used data from the Beginning Postsecondary Students Longitudinal Study to examine the demographic and in-college characteristics of students with disabilities at 2-year institutions, identify the types of educational services available to them, and determine how students' disability conditions and their selected demographic and…

Early school-leaving imposes costs on the individual and society, and is linked to factors including gender, family income and parental education, community deprivation, and academic history. In Ireland, the role of the school in shaping patterns of early school-leaving is unclear. Employing the Theory of Planned Behaviour (TPB) from social…

Data collected from two major universities (one in the Midwest and one in the Southeast) in the United States were used to analyze student persistence behavior and perceptions of debt. Results from four separate logistic regression analyses suggested that financial factors play a significant role in student persistence behavior as well as in…

This research brief provides highlights from the full report (published separately). In the report on AISD students, with a focus on the graduating class of 2009, the most powerful predictors of overall student dropout risk were having an 8th-grade attendance rate of less than 90% and failing both the 8th-grade reading and math TAKS tests. [For…

Computer-based social networking has become ubiquitous on college and university campuses. However, little is known about how this form of networking reflects social integration which is considered to be an integral component of student persistence. To address this topic, a random sample of 375 entering freshman were used to evaluate the…