Nowadays, the main aim of every engineering college or university is the improvement of the educational outcome. The student's academic performance mainly impacts the educational outcome of any college. Measuring students' performance is a challenging issue that can help students and teachers to keep track progress of student performance and there by mentoring less performance students to obtain the highest grade in their final exams. The present work will help in predicting the performance of

more »

... very student within 2 weeks of 16 weeks instruction period using previous outcome in various examinations and some additional parameters also effects the students' academic performance such as attendance, health issues, etc. Based on the predicted results student can be monitored to improve his/her abilities. To achieve this, this study proposes a deep multilayer feed forward neural network (MFFNN) model. The proposed model is used to predict the performance of every individual for a single subject or a course with high accuracy. In this paper, a dataset is generated based on the previous exam grades and a set of handcrafted features of students. The results indicate the proposed MFFNN model achieves an accuracy of 89.19% -93.89 %. The proposed model outperforms the support vector machine. While the support vector machine achieves 76.71% -88.6%. This study makes an open door for recognizing students who may graduate with poor outcomes or may not graduate at all, and also to assist intuitions and instructors for early intervention.