Back to the Basics: Bayesian extensions of IRT outperform neural networks for proficiency estimation

TL;DR

This paper demonstrates that Bayesian IRT models, especially hierarchical and temporal extensions, outperform neural network approaches like DKT in student proficiency estimation across various datasets, offering better interpretability and performance.

Contribution

The paper introduces Bayesian IRT extensions that outperform neural network models in proficiency estimation, highlighting their simplicity, interpretability, and effectiveness across datasets.

Findings

IRT-based methods match or outperform DKT in predictions

Hierarchical IRT captures item grouping structure effectively

Temporal IRT improves performance with autocorrelated data

Abstract

Estimating student proficiency is an important task for computer based learning systems. We compare a family of IRT-based proficiency estimation methods to Deep Knowledge Tracing (DKT), a recently proposed recurrent neural network model with promising initial results. We evaluate how well each model predicts a student's future response given previous responses using two publicly available and one proprietary data set. We find that IRT-based methods consistently matched or outperformed DKT across all data sets at the finest level of content granularity that was tractable for them to be trained on. A hierarchical extension of IRT that captured item grouping structure performed best overall. When data sets included non-trivial autocorrelations in student response patterns, a temporal extension of IRT improved performance over standard IRT while the RNN-based method did not. We conclude that IRT-based models provide a simpler, better-performing alternative to existing RNN-based models of student interaction data while also affording more interpretability and guarantees due to their formulation as Bayesian probabilistic models.