Evidence on the extent to which dropout intention can serve as a valid predictor of dropout decisions remains scarce. This study first presents the results of a systematic literature review of 14 studies examining the relationship between dropout intention and actual dropout in post-secondary education (vocational education and training [VET] or…

Student drop-out is one of the most burning issues in STEM higher education, which induces considerable social and economic costs. Using machine learning tools for the early identification of students at risk of dropping out has gained a lot of interest recently. However, there has been little discussion on dropout prediction using interpretable…

In recent times, Educational Data Mining and Learning Analytics have been abundantly used to model decision-making to improve teaching/learning ecosystems. However, the adaptation of student models in different domains/courses needs a balance between the generalization and context specificity to reduce the redundancy in creating domain-specific…

Colleges have increasingly turned to predictive analytics to target at-risk students for additional support. Most of the predictive analytic applications in higher education are proprietary, with private companies offering little transparency about their underlying models. We address this lack of transparency by systematically comparing two…

This study explores a variety of variables with the intent of identifying specific student groups that may struggle with performance in a large general education course. The ultimate objective of this study is to facilitate the success of acknowledged at-risk students. Drawing in part on the theory of social capital, this study examines…

Nathanael Okpych and Mark Courtney review barriers to completing a college degree for young adults with foster care histories seeking post-secondary education. Their longitudinal approach evaluates students with foster care histories attending 2- and 4-year colleges and compares outcomes with low-income first-generation college students over a…

Early warning systems are being used to assist students in their studies as well as understanding student behaviour and performance better. A home-grown EWS plug-in for Moodle was used to predict the student performance in a first year IT literacy course at University of the South Pacific. The alert tool was designed to capture student logins,…

Part II of the Houston Longitudinal Study on the Transition to College and Work (HLS) examined potential indicators of college enrollment school and district staff might use to identify and support students at risk of not attending college. The study used administrative data from the Houston Independent School District (HISD) and tracked two…

This report examined three potential indicators of college enrollment school and district staff might use to identify and support students at risk of not attending college: (1) Chicago: Designed to predict high school graduation; based on earning six course credits--the minimum to advance to the next grade in HISD--and having at most one semester…

These are the appendices for "Transitioning to College and Work. Part 2: A Study of Potential Enrollment Indicators," which examined potential indicators of college enrollment school and district staff might use to identify and support students at risk of not attending college. The study used administrative data from the Houston…

Early-warning intervention for students at risk of failing their online courses is increasingly important for higher education institutions. Students who show high levels of engagement appear less likely to be at risk of failing, and how engaged a student is in their online experience can be characterized as factors contributing to their social…

This quantitative study examined the influence of family, school, and peers on the educational aspirations of African American male high school students in the ninth and tenth grade who live in a small Midwest town. Increasing the higher education aspirations of African American males is the first step needed to attend college, which according to…

Learning analytics and digital badges are emerging research fields in educational science. They both show promise for enhancing student retention in higher education, where withdrawals prior to degree completion remain at about 30% in Organisation for Economic Cooperation and Development member countries. This integrative review provides an…

This investigation sought to determine when colleges should conduct assessments to identify first-year students at risk of dropping out. Thirty-five variables were used to predict the persistence of 2,024 first-year students from four universities in the southeastern United States. The predictors were subdivided into groups according to when they…

Along with the massification of higher education and increasing costs, the pressure on institutions to retain all students to degree completion has been mounting. Early identification of students who are at risk of leaving an institution may help institutions to target and retain these students. This study investigated whether freshmen behaviors,…