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…

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…

Dropout is a global crisis and an affliction in the United States. This study analyzes graduation rates based on prior academic achievement, attendance, and behavior at an urban American high school in Virginia over 4 years to identify who is (not) graduating and why. Using a correlational, nonexperimental design, four cohorts of graduates were…

Even prior to the COVID-19 pandemic, online learning had become a fundamental part of post-secondary education. At the same time, empirical evidence from the last decade documents higher dropout online in comparison to face-to-face courses for some students. Thus, while online learning may provide students access to post-secondary education,…

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 dropout rate is the most significant disadvantage in Massive Open Online Courses (MOOC); most of the time, it exceeds 90%. This research compares the effect of cognitive bias, gamification, monetary compensation, and student characteristics (gender, age, years of education, student geographical location, and interest in the course certificate)…

The decline in doctoral program completion has become one of the main challenges in doctoral education worldwide. As concern about this issue grows, the number of studies examining the topic has also increased. Many of these studies, which aim to identify the factors that contribute to high attrition rates, rely on cross-sectional data and often…

The aim of this work is to provide data-driven insights regarding the factors behind dropouts in Higher Education and their impact over time. To this end, we analyzed students' data collected by a Higher Education Institute over the last 11 years and we explored how socio-economic and academic changes may have impacted student dropouts and how…

This paper examines the role of sociodemographic characteristics on non-traditional mature freshmen higher education dropout rates. One of Chile's largest higher education institutions, which has an important number of mature students from more deprived social sectors, was used as a case study. A quantitative methodology was applied, based on the…

Despite the importance of obtaining a university degree, retention rates remain a concern for many universities. This longitudinal study provides a multi-domain examination of first-year student characteristics and behaviors that best predict which students graduate. Graduation status was assessed seven years after students entered university.…

Purpose: This study aims to advance the understanding on individual variations in PhD candidates' personal interest in their doctorate and supervisory and research community support, and several individual and structural attributes potentially having an impact on the profiles. Design/methodology/approach: The authors explored the interrelationship…

This paper introduces a novel approach to identify at-risk students with a focus on output interpretability through analyzing learning activities at a finer granularity on a weekly basis. Specifically, this approach converts the predicted output from the former weeks into meaningful probabilities to infer the predictions in the current week for…

Using administrative data from an urban school district, two series of predictive models were tested for their ability to project a student's high school graduation status. The models included student grades, attendance, behavior, demographic predictors, and school-level variables. Eighth and ninth-grade variables were tested for two graduation…

The purpose of this paper is to investigate the pre-enrollment attributes of first-year students at Computer Science BSc programs of the University of Miskolc, Hungary in order to find those that mostly contribute to failure on the Programming Basics first-semester course and, consequently to dropout. Our aim is to detect at-risk students early,…