Accurate Predictions in Education with Discrete Variational Inference

This paper introduces a probabilistic modeling framework using Item Response Theory and novel discrete variational inference to predict whether K-12 students will answer mathematics exam questions correctly, releasing the largest open dataset of professionally marked formal mathematics exam responses. The work achieves over 80% prediction accuracy and demonstrates that a single latent ability parameter may be sufficient for accurate predictions, with particular strength in low-data cold-start scenarios.

One of the largest drivers of social inequality is unequal access to personal tutoring, with wealthier individuals able to afford it, while the majority cannot. Affordable, effective AI tutors offer a scalable solution. We focus on adaptive learning, predicting whether a student will answer a question correctly, a key component of any effective tutoring system. Yet many platforms struggle to achieve high prediction accuracy, especially in data-sparse settings. To address this, we release the lar

Study Type

Source

Framework Categories

Tool Types

Tags