Empirical Evaluation of Deep Learning Models for Knowledge Tracing: Of Hyperparameters and Metrics on Performance and Replicability

New knowledge tracing models are continuously being proposed, even at a pace where state-of-theart models cannot be compared with each other at the time of publication. This leads to a situation where ranking models is hard, and the underlying reasons of the models’ performance – be it architectural choices, hyperparameter tuning, performance metrics, or data – is often underexplored. In this work, we review and evaluate a body of deep learning knowledge tracing (DLKT) models with openly available and widely-used data sets, and with a novel data set of students learning to program. The evaluated knowledge tracing models include Vanilla-DKT, two Long Short-Term Memory Deep Knowledge Tracing (LSTM-DKT) variants, two Dynamic Key-Value Memory Network (DKVMN) variants, and Self-Attentive Knowledge Tracing (SAKT). As baselines, we evaluate simple non-learning models, logistic regression and Bayesian Knowledge Tracing (BKT). To evaluate how different aspects of DLKT models influence model performance, we test input and output layer variations found in the compared models that are independent of the main architectures. We study maximum attempt count options, including filtering out long attempt sequences, that have been implicitly and explicitly used in prior studies. We contrast the observed performance variations against variations from non-model properties such as randomness and hardware. Performance of models is assessed using multiple metrics, whereby we also contrast the impact of the choice of metric on model performance. The key contributions of this work are the following: Evidence that DLKT models generally outperform more traditional models, but not necessarily by much and not always; Evidence that even simple baselines with little to no predictive value may outperform DLKT models, especially in terms of accuracy – highlighting importance of selecting proper baselines for comparison; Disambiguation of properties that lead to better performance in DLKT models including metric choice, input and output layer variations, common hyperparameters, random seeding and hardware; Discussion of issues in replicability when evaluating DLKT models, including discrepancies in prior reported results and methodology. Model implementations, evaluation code, and data are published as a part of this work