On predicting school dropouts in Egypt: A machine learning approach

Abstract

Compulsory school-dropout is a serious problem affecting not only the education systems, but also the developmental progress of any country as a whole. Identifying the risk of dropping out, and characterizing its main determinants, could help the decision-makers to draw eradicating policies for this persisting problem and reducing its social and economic negativities over time. Based on a substantially imbalanced Egyptian survey dataset, this paper aims to develop a Logistic classifier capable of early predicting students at-risk of dropping out. Training any classifier with an imbalanced dataset, usually weaken its performance especially when it comes to false negative classification. Due to this fact, an extensive comparative analysis is conducted to investigate a variety of resampling techniques. More specifically, based on eight under-sampling techniques and four over-sampling ones, and their mutually exclusive mixed pairs, forty-five resampling experiments on the dataset are conducted to build the best possible Logistic classifier. The main contribution of this paper is to provide an explicit predictive model for school dropouts in Egypt which could be employed for identifying vulnerable students who are continuously feeding this chronic problem. The key factors of vulnerability the suggested classifier identified are student chronic diseases, co-educational, parents' illiteracy, educational performance, and teacher caring. These factors are matching with those found by many of the research previously conducted in similar countries. Accordingly, educational authorities could confidently monitor these factors and tailor suitable actions for early intervention.

Potential Risks of Artificial Intelligence Integration into School Education: A Systematic Review

“…Identifying students at risk of dropping out school is a difficult task. Machine learning system of AI technology is increasingly used to early predict students at-risk of school-dropout for reducing its negative social and economic implications (Mduma, 2023; Selim & Rezk, 2023). The system is able to identify students at risk of dropping out school based on previous database of a student (students’ learning pattern and performance, percentage of attendance, monitoring his/her school activity etc.).…”

Translating sophisticated data analytic strategies regarding school attendance and absenteeism into targeted educational policy

“…Chung and Lee (2019) employed random forests to predict dropout among Korean high school students, though predictors of non-dropouts were stronger. These analyses highlight the importance of non-academic measures for understanding the impact of absenteeism and school dropout risk (see also Colak Oz et al, 2023;Mnyawami et al, 2022;Selim & Rezk, 2023).…”

Institutional and Teaching Practices for Student Retention: Accounts from Four High Schools of Valparaíso, Chile

“…On the other hand, there remains a high interest in continuing to delve into the causes that cause it, either in a general way (Kumar et al, 2023) or by analyzing specific factors such as parental alcohol consumption (Pisinger et al, 2023). Some studies analyze this topic using more sophisticated techniques, such as machine learning (Colak Oz et al, 2023;Selim & Rezk, 2023). Within these cases is a Chilean study, which, based on this methodology, achieved a model with a predictive capacity 20% higher than previous studies (Rodríguez et al, 2023).…”