Machine Learning Predicts Upper Secondary Education Dropout as Early as the End of Primary School

Aug 4, 2026

Upload by Aria

Education shapes outcomes that extend beyond individuals, yet persistent school dropout undermines progress across economic, social, and personal development. Prior machine-learning dropout work often relies on short-term data collected only a few years into the observation window. This study extends the prediction horizon using a 13-year longitudinal dataset covering kindergarten through Grade 9, leveraging academic and cognitive skills, motivation, behavior, well-being, and official dropout records. Models achieved mean AUC 0.61 up to Grade 6 and improved to 0.65 up to Grade 9, supporting early-risk identification.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Education and the consequences of dropout

Scale and context of dropout challenges

Machine learning in education

Prior ML studies and limitations

arXiv :2403 . 14663v1 [ cs .CY] 1 Mar 2024 Machine Learning Predicts Upper Secondary Education Dropout as Early as the End of Primary School Maria Psyridou 1,* , Fabi Prezja2 , Minna Torppa3 , Marja-Kristiina Lerkkanen3 , Anna-Maija Poikkeus3 , and Kati Vasalampi4 1 Department of Psychology, University of Jyvskyl, 40014, Jyvskyl, Finland 2 Faculty of Information Technology, University of Jyvskyl, 40014, Jyvskyl, Finland 3 Department of Teacher Education, University of Jyvskyl, 40014, Jyvskyl, Finland 4 Department of Education, University of Jyvskyl, 40014, Jyvskyl, Finland * [maria.m.psyridou@jyu.fi](maria.m.psyridou@jyu.fi) ABSTRACT Education plays a pivotal role in alleviating poverty, driving economic growth, and empowering individuals, thereby significantly influencing societal and personal development. However, the persistent issue of school dropout poses a significant challenge, with its effects extending beyond the individual. While previous research has employed machine learning for dropout classification, these studies often suffer from a short-term focus, relying on data collected only a few years into the study period. This study expanded the modeling horizon by utilizing a 13-year longitudinal dataset, encompassing data from kindergarten to Grade 9 . Our methodology incorporated a comprehensive range of parameters, including students’ academic and cognitive skills, motivation, behavior, well-being, and officially recorded dropout data. The machine learning models developed in this study demonstrated notable classification ability, achieving a mean area under the curve (AUC) of 0.61 with data up to Grade 6 and an improved AUC of 0.65 with data up to Grade 9 . Further data collection and independent correlational and causal analyses are crucial. In future iterations, such models may have the potential to proactively support educators’ processes and existing protocols for identifying at-risk students, thereby potentially aiding in the reinvention of student retention and success strategies and ultimately contributing to improved educational outcomes. Introduction Education is often heralded as the key to poverty reduction, economic prosperity, and individual empowerment, and it plays a pivotal role in shaping societies and fostering individual growth 1–3. However, the specter of school dropout casts a long shadow, with repercussions extending far beyond the individual. Dropping out of school is not only a personal tragedy but also a societal concern; it leads to a lifetime of missed opportunities and reduced potential alongside broader social consequences, including increased poverty rates and reliance on public assistance. Existing literature has underscored the link between school dropout and diminished wages, unskilled labor market entry, criminal convictions, and early adulthood challenges, such as substance use and mental health problems4–7. The socioeconomic impacts, which range from reduced tax collections and heightened welfare costs to elevated healthcare and crime expenditures, signal the urgency of addressing this critical issue8. Therefore, understanding and preventing school dropout is crucial for both individual and societal advancement. Beyond its economic impact, education differentiates individuals within the labor market and serves as a vehicle for social inclusion. Students’ abandonment of the pursuit of knowledge translates into social costs for society and profound personal losses. Dropping out during upper secondary education disrupts the transition to adulthood, impedes career integration, and compromises societal well-being9. The strong link between educational attainment and adult social status observed in Finland and globally 10 underscores the importance of upper secondary education as a gateway to higher education and the labor market. An increase in school drop-out rates in many European countries 11 is leading to growing pockets of marginalized young people. In the

FAQs

Why is predicting school dropout early considered important?

The document highlights that dropout affects individuals and society through lost opportunities, reduced labor-market potential, and broader socioeconomic costs.

What data and modeling horizon does this study use?

It uses a 13-year longitudinal dataset spanning kindergarten through Grade 9, including students’ academic and cognitive skills, motivation, behavior, well-being, and official dropout data.

How accurate were the machine learning models?

The models achieved a mean AUC of 0.61 using data up to Grade 6, improving to 0.65 when data extended to Grade 9.

Aug 4, 2026

Upload by Aria