Student Modeling Method Integrating Knowledge Tracing and IRT with Decay Effect

Abstract. Educational data mining (EDM) involves the application of data mining, machine learning, and statistics to information generated from educational settings. Modeling students' knowledge is a fundamental part of intelligent tutoring systems. One of the most popular methods for estimating students' knowledge is knowledge tracing. It is the de-facto standard for inferring students' knowledge from performance data. The goal of this study is to estimate future student performance from massive amounts of examination results. We propose a novel method to improve the precision of student modeling using knowledge tracing with item response theory, including the decay theory of forgetting