Prediction of Students' Educational Status Using CART Algorithm, Neural Network, and Increase in Prediction Precision Using Combinational Model

In this paper, using CART and Neural Network data mining algorithms we have dealt with the study of effective factors in the rate of becoming unqualified among students of Payame Noor University of Qom Province. After creating models using algorithms separately, we have combined models in Clementine 12.0 software through Ensemble Node and have created the combinational model and finally with Analysis Node we have evaluated models and compared results. In the created model using neural network algorithm, in input layer 44 neurons, in hidden layer 3 neurons, and in output layer 1 neuron are created, also in CART model a decision tree with depth of 5 is created. Considering that the number of fields in data bank is high, using Feature Selection Node and selecting the target, we have deleted those fields that had less influence on the target. This matter has decreased the model complexity to some extent.