Abstract: Knowledge tracing (KT), the task of tracking the knowledge state of each student over time, has been assessed actively by artificial intelligence researchers. Recent reports describe that deep-IRT, which combines Item Response Theory (IRT) with a deep learning model, provides superior performance. It can express each student’s ability and the difficulty of each item such as IRT. However, its interpretability and applicability remain limited compared to those of IRT because item and ability parameter estimates depend on the order of the presented items. The method hinders interpretation of a student’s ability estimate and its application to adaptive learning, which presents optimal contents to a student. To overcome those difficulties, this study proposes a novel Deep-IRT model,which models a student’s response to an item by two independent networks: a student network and an item network. Experiments demonstrate that the proposed model outperforms the previous KT models.