Predicting Student Retention and Success in Higher Education

Student retention and success remain persistent global challenges in higher education, with direct implications for institutional quality, resource allocation, and social equity. While many factors influence dropout or progression, quantitative approaches have enabled deeper insights into patterns of academic persistence and completion. Over the past two decades, predictive analytics - fueled by advances in educational data mining and statistical modeling - have become increasingly prominent in identifying at-risk students and forecasting academic outcomes. However, much of the literature remains context-specific, methodologically diverse, and fragmented across disciplines. This Research Topic seeks to consolidate quantitative research efforts that examine and predict retention, success, and other student movement patterns in higher education through robust, generalizable methodologies.

This Research Topic aims to advance the understanding of student retention and success in higher education through rigorous, data-driven approaches that reflect the complexity of student movement pattern. Despite institutional efforts to enhance throughput and reduce attrition, many interventions remain reactive or insufficiently informed by predictive evidence. This gap underscores the need for robust statistical and machine learning models that can identify significant predictors of persistence and success early in the academic journey. We aim to gather high-quality contributions that develop or validate predictive models using diverse quantitative methods—ranging from logistic regression, structural equation modeling, and survival analysis, to more contemporary approaches such as artificial intelligence and learning analytics. The goal is to encourage comparative, cross-institutional, and context-sensitive research that not only enhances predictive accuracy but also informs early warning systems, targeted interventions, and inclusive retention policies. This research topic will support the development of replicable, ethically sound, and policy-relevant knowledge to improve student outcomes globally.

We invite original quantitative research articles, systematic reviews, data reports, and methodological papers focused on predicting student retention and success in higher education. While retention is commonly defined as continuous re-registration, we encourage submissions that address its broader complexity, including year-to-year enrolment, term-based persistence, and spiraling behaviors such as pausing-out, stopping-out, or dropping-out. Submissions may address, but are not limited to:

• Development and validation of predictive models;
• Identification of key academic, behavioral, psychosocial, or demographic predictors;
• Institutional applications of predictive analytics;
• Comparative studies across higher education systems;
• Evaluation of early-warning systems and predictive dashboards;
• Methodological innovations in modeling retention/success.

Priority will be given to contributions that employ rigorous quantitative techniques, are grounded in sound theoretical frameworks, and demonstrate practical implications for higher education policy and practice. Manuscripts should provide sufficient detail to ensure reproducibility and transparency in methods and findings.

Keywords: Student retention, Student success, Predictive analytics, Quantitative, Higher Education

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.