Extending Deep Knowledge Tracing: Inferring Interpretable Knowledge and Predicting Post-System Performance

Recent student knowledge modeling algorithms such as DKT and DKVMN have been shown to produce accurate predictions of problem correctness within the same learning system. However, these algorithms do not generate estimates of student knowledge. In this paper we present an extension that infers knowledge estimates from correctness predictions. We apply this extension to DKT and DKVMN, resulting in knowledge estimates that correlate better with a posttest than knowledge estimates produced by PFA or BKT. We also apply our extension to correctness predictions from PFA and BKT, finding that knowledge predictions produced with it correlate better with the posttest than BKT and PFA's own knowledge predictions. These findings are significant since the primary aim of education is to prepare students for later experiences outside of the immediate learning activity.