Uncertainty-preserving deep knowledge tracing with state-space models

This paper introduces Dynamic LENS, a deep learning model that combines deep knowledge tracing with uncertainty quantification to track student knowledge over time while preserving measurement error estimates, bridging formative practice systems and summative assessment approaches. The model uses variational autoencoders and Bayesian state-space models to integrate student response data across time while treating responses from the same test as exchangeable observations.

A central goal of both knowledge tracing and traditional assessment is to quantify student knowledge and skills at a given point in time. Deep knowledge tracing flexibly considers a student's response history but does not quantify epistemic uncertainty, while IRT and CDM compute measurement error but only consider responses to individual tests in isolation from a student's past responses. Elo and BKT could bridge this divide, but the simplicity of the underlying models limits information sharing

Source

Framework Categories

Tool Types

Tags