In this paper gaze prediction aims to acquire the good performance via “Convolutional Neural Network (CNN” based identification. Gaze prediction was proposed to localize the gaze direction of the students in classrooms us-ing captured face images. Such systems can raise the teachers’ awareness whether students are gazing towards him or not, and also alert the students to pay attention to their teachers if their gazes were scattered. In this way, pre-diction of gaze was proposed firstly to achieve the propose eyes area detec-tion algorithm based on modeling facial gestures. The inputs of the gaze pre-diction are the output of the eyes detection. Secondly, the localizing gaze of the students had been considered as straight, right or left. CNN was em-ployed to different training models for the gaze prediction phase. The dataset was obtained from a public database for neural network training.