In the contemporary era, the landscape of innovation and entrepreneurship is dynamically evolving, fueled by a substantial surge in venture capital investments and the rapid expansion of the global startup ecosystem. This burgeoning growth not only highlights the vibrant nature of modern economies but also brings to the forefront the critical…

This quantitative study investigates the predictive power of machine learning (ML) models on degree completion among adult learners in higher education, emphasizing the enhancement of data-driven decision-making (DDDM). By analyzing three ML models - Random Forest, Gradient-Boosting machine (GBM), and CART Decision Tree - within a not-for-profit,…

Colleges and universities are increasingly turning to algorithms that predict college-student success to inform various decisions, including those related to admissions, budgeting, and student-success interventions. Because predictive algorithms rely on historical data, they capture societal injustices, including racism. In this study, we examine…

Colleges and universities are increasingly turning to algorithms that predict college-student success to inform various decisions, including those related to admissions, budgeting, and student-success interventions. Because predictive algorithms rely on historical data, they capture societal injustices, including racism. In this study, we examine…

Statistics Canada releases data on the labour market outcomes of college and university graduates using data from the Education and Labour Market Longitudinal Platform (ELMLP). Statistics Canada has developed the ELMLP in collaboration with the provincial and territorial ministries of education, Employment and Social Development Canada (ESDC), and…

The growing use of analytics has increased the demand for more highly data literate graduates. Awareness of ambiguity in data has been suggested as a new data literacy skill. Here, we describe a student-centered semester-long project that can be used to teach this skill in an introductory analytics or database course. The project requires students…

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 quantitative based applied research study examined data collected fromstudents who have withdrawnfromor completed aneducator preparation program (EPP) ina small rural public community college in WestVirginia. This study compared studentretention rates with Frontier andRemote (FAR) designation by home zip code. These data informedthe research…

In this paper, we present an extended evaluation of a course recommender system designed to support students who struggle in the first semesters of their studies and are at risk of dropping out. The system, which was developed in earlier work using a student-centered design, is based on the explainable k-nearest neighbor algorithm and recommends a…

This study presents a data mining approach to predict academic success of the first-year students. A dataset of 10 academic years for first-year bachelor's degrees from a Portuguese Higher Institution (N = 9652) has been analysed. Features' selection resulted in a characterising set of 68 features, encompassing socio-demographic, social origin,…

Student dropout is a significant concern for university administrators, students and other stakeholders. Dropout is recognised as highly complex due to its multi-causality, which is expressed in the existing relationship in its explanatory variables associated with students, their socio-economic and academic conditions, and the characteristics of…

Objective/Research Question: Community college graduation rates are typically quite low, and developmental mathematics enrollment and coursetaking patterns may constrain academic outcomes. To identify ways in which community college graduation rates may be improved, decision trees were utilized to examine the STEM coursetaking patterns of N =…

The purpose of this brief is to provide school-level examples of how early college practitioners are collecting and using data to improve their practices. Examples three and four are school-level data from two early college partnerships: the MetroWest CPC (Framingham, Milford, Waltham), and Lawrence. The brief begins, however, with the national…

Higher education institutions have prioritized supporting undecided students with their major and career decisions for decades. This study used a U.S. public research-focused university's large-scale institutional data set and undecided student's retention and graduation rate predictors to demonstrate how to couple student and institutional data…

Data-driven decision making is a critical leadership skill. This study describes how leadership at a four-year university used extant data to improve student outcomes. The University identified the high rate of first-time-in-college (FTIC) student withdrawal/failure in initial algebra courses as having a detrimental effect on other student success…