September 11, 2025PLoS ONEOpen Access

A hybrid framework of statistical, machine learning, and explainable AI methods for school dropout prediction

View Full Paper

Ask AI

Bookmark

The XGB model achieved a remarkable accuracy of 94.4%, indicating its effectiveness in predicting school dropout.
Key predictors identified include age, sex, and parents' education, highlighting socio-economic influences.
Statistical analysis combined with machine learning techniques provided robust predictive capabilities for school dropout.
Employing SHAP and LIME ensures transparency in model predictions, critical for educational policymakers.

Discussion

No takes yet. Share an insight, caveat, or question.

Analyzing dropout factors in students aged 6–24 years in Bangladesh, suggesting effective interventions.

Khatun et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark