Peer-reviewed article
Beyond health: A machine learning analysis of structural barriers to school attainment in Somalia.
Ali JA, Cumar MA, Abdi MK, Muse AH, Abdikarim H ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This study analyzed data from over 10,000 Somali children to understand why some do not attend school. Using machine learning techniques, researchers found that where a child lives, how old they are, and whether their family is nomadic are the strongest predictors of school non-attendance, more important than health or poverty alone. Non-attendance increased from 6% in younger children to 25% in teenagers, and reached 30.5% in Middle Shabelle region. The findings suggest that targeted policies addressing regional disparities and the needs of nomadic populations would be more effective than broad, single-sector approaches.
Key points
- Age is a major barrier: school non-attendance rises from 6% in 6-10 year-olds to 25% in 15-18 year-olds
- Geographic region strongly predicts non-attendance, with Middle Shabelle reaching 30.5% non-attendance
- Nomadic children face triple the non-attendance risk compared to their settled peers
- Structural and demographic factors outweighed direct health status or household poverty as predictors
- Policy should prioritize geographically-targeted and age-specific strategies rather than broad approaches
Limitations
This analysis is descriptive and identifies correlations rather than causal relationships. The study cannot determine whether observed barriers directly cause school non-attendance or whether other unmeasured factors drive both the barriers and the educational outcomes.
Abstract
In fragile states like Somalia, the link between poor health and educational exclusion is critical yet poorly understood. This study uses a novel machine learning approach to identify and rank the most significant barriers to school attendance. We analyzed nationally representative data from 10,511 children aged 6-18 in the 2022 Somalia Integrated Household Budget Survey (SIHBS). Ten supervised machine learning models were employed to predict school attendance, with the Random Forest model emerging as the top performer (AUC = 0.86). Contrary to conventional wisdom, our findings reveal a clear hierarchy of barriers where structural and demographic factors are the most powerful predictors. A child's age (non-attendance rises from 6% in 6-10 year-olds to 25% in 15-18 year-olds), geographic region (non-attendance reaches 30.5% in Middle Shabelle), and residence type (nomadic children face triple the non-attendance risk of their peers) were the dominant determinants. These factors significantly outweighed the direct predictive power of individual health status or household poverty. The results indicate that while health is important, educational exclusion in Somalia is more fundamentally driven by where a child lives, how old they are, and their family's mode of life. Policy interventions must therefore shift from broad, single-sector approaches to geographically-targeted, age-specific strategies. To effectively address the root causes of educational inequality, efforts should prioritize service delivery in marginalized regions and provide tailored support for nomadic and adolescent populations.