Prediction of Pass Rate Using Neural Networks

In this paper, neural networks applied to predict the pass rate (percentage) for a particular examination of a particular student based on some auxiliary information. The data of 500 students is divided into three sets first two sets are used to training and validation of the neural networks and third set is used for testing. Training and validation is continued until the parameters of neural network are generalized. Then this network is applied on testing set to predict the pass rates. This data is analyzed through the feedforward neural networks and it presents promising results on prediction of pass rate. The prediction efficiency is measured by computing mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) for the testing set.