Optimizing Student Success Predictions using Artificial Intelligence

This work investigates using AI and neural networks to enhance predictions of student success and optimize resource allocation in education, finding that advanced models can significantly improve support for students and address resource imbalances.

The education field and literacy rates remain popular subjects of discussion within both the research community and the AI field, as people continually seek ways to promote learning and enhance literacy. This work aims to examine the extent of how predictions of students’ success in school can be improved by using AI models and neural networks with respect to student performance, and consequently study more effective resource allocation among students. We concentrate on exploiting artificial neural networks to predict student results; using information about academic history, socio-economic status, attendance rates and engagement levels etc., which inform the allocation of resources like educational materials, teachers, technology devices, & mentors accordingly. We tested different models, including Linear Regression, Logistic Regression and Decision Decision Trees, and neural networks with dense layers. The study finds that using advanced predictive models can greatly increase the types of educational support we offer, reduce disparities in student performance, and address issues revolving around how and where resource allocations may be most equitable. Therefore, we propose a strand of research to mitigate educational resource imbalances and better support low-attainment students with targeted interventions informed by predictive analytics.

Explore More!

Research Paper