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…

This study examines whether tutors (N?=?15) in a problem-based learning curriculum were able to predict students' success in their first year and their entire bachelor programme. Tutors were asked to rate each student in their tutorial group in terms of the chance that this student would successfully finish their first year and the entire…

The present study tested the hypothesis that the international undergraduates at a West Coast American public university during recent years of dramatic enrollment growth should have low retention and graduation rates. This study showed instead that these students were retained and graduated at rates surpassing predictions from research and…

The underrepresentation of racial minorities and women in science, technology, engineering, and mathematics (STEM) disciplines is a national concern. Goal theory provides a useful framework from which to understand issues of underrepresentation. We followed a large sample of high-achieving African American and Latino undergraduates in STEM…

A study by Kenney, Kenney, and Dumont (2005) identified a supportive learning environment as one of the five indicators for collegiate student engagement, a concept that extends beyond the classroom to permeate the entire educational environment. A student's level of engagement can be impacted as early as orientation and registration, when he is…

Affecting university rankings, school reputation, and financial well-being, student retention has become one of the most important measures of success for higher education institutions. From the institutional perspective, improving student retention starts with a thorough understanding of the causes behind the attrition. Such an understanding is…

Analysis of data on 101 entering proprietary college students found that (1) predictors of initial achievement were entrance exam scores, gender, race, age, grade point average, and expectations; (2) dropout predictors were marital status, work hours, prior achievement, absences, and faculty interaction; and (3) age, gender, race, and children did…

The incorporation of computer-managed instruction into an academic program made it necessary to identify those cognitive styles, abilities, and aptitudes which were relevant to the success or failure of trainees in the Navy's Basic Electricity and Electronics (BE/E) School in order to minimize the attrition rate. Measures of 6 styles, 6 abilities,…

Data from a standardized reading test and student background information were correlated to determine relationships. Self-assessed reading scores and other data may be used for predicting retention, academic performance, and reading ability. Differences were found between persisters and dropouts on these variables. (Author)

In a study of college student retention and progression, significant differences were found between black and white students in terms of their attrition rates, overall progression rates, and tendency to follow the prescribed progression pattern. When other student and institutional characteristics are statistically controlled, racial differences…

Research on student withdrawals has largely ignored the issue of stop-outs, those students who withdraw from a college or university but subsequently reenroll. As a result, student withdrawals have been seen as an attrition issue. However, this study suggests they should be viewed as a retention possibility rather than an attrition issue. This…

The 7th International Conference on Education Data Mining held on July 4th-7th, 2014, at the Institute of Education, London, UK is the leading international forum for high-quality research that mines large data sets in order to answer educational research questions that shed light on the learning process. These data sets may come from the traces…