Determining Students Performance Using the Tool of Artificial Neural Network


Jateen Shet Shirodkar
Viren Pereira


Technical Education has grown rapidly over a few decades and is one of the key drivers in the knowledge driven economy. The systematic growth of quality in technical education plays a vital role in development. In any academic organization, early prediction of student's performance is very important to management so that strategic intervention can be pre-planned before they could appear for the semester examination. Artificial Neural Network (ANN) is a superior mathematical tool used to identify trends in data by developing relationships between various inputs and outputs. Feed Forward Back Propagation Network (BPN) is powerful technique of ANN as it can simulate any continuous or non-linear function. The proposed model allows prediction using a Feed Forward Neural Network (FFNN). The trained model helps to accurately predict at-risk students and reduces the student dropout rate. The output of this study showed that first semester percentage is strongly influenced by fundamental subjects. Comparison between predicted and actual output indicated that the ANN model holds promise for estimation of student's performance.