In Intelligent Tutoring System (ITS), tracing the student's knowledge state\nduring learning has been studied for several decades in order to provide more\nsupportive learning instructions. In this paper, we propose a novel model for\nknowledge tracing that i) captures students' learning ability and dynamically\nassigns students into distinct groups with similar ability at regular time\nintervals, and ii) combines this information with a Recurrent Neural Network\narchitecture known as Deep Knowledge Tracing. Experimental results confirm that\nthe proposed model is significantly better at predicting student performance\nthan well known state-of-the-art techniques for student modelling.\n