Abstract
Explainable Artificial Intelligence has emerged as a critical tool in addressing the transparency challenges associated with machine learning models. This study investigates the application of XAI techniques in the educational domain, with a focus on identifying factors influencing academic performance. Using datasets encompassing student demographics, academic achievements, and contextual variables, machine learning models were developed and analyzed using SHapley Additive exPlanations. The results highlighted the significance of higher qualification achievements and early academic milestones, such as num_level_3_at_age_18 and num_key_stage_2_attainment. These findings corroborate existing literature while providing novel insights through visual and interpretable analytics. The study demonstrates the transformative potential of XAI in uncovering actionable insights, offering policymakers and educators tools to address disparities in educational outcomes. The novelty of applying XAI in this context lies in its ability to bridge the gap between complex predictive models and practical decision-making. Future research directions include expanding datasets to incorporate diverse educational settings and developing real-time educational tools based on interpretability insights. This work lays the foundation for leveraging XAI to drive equity and excellence in education.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call