In this paper authors propose transformer model that would solve knowledge tracing problem. Student learning process largely depends on his/her past learning experience and the skills that (s) he acquired in the past while solving the tasks. SAKT(self attentive model fro knowledge tracing) firstly identifies KCs. In this papers exercises were used as KCs. Their model assigns weights for the previously solved items and then predicts the probability of answering particular question correctly. Their model outperformed previous models by 4.43% gain in AUC score.