Predicting The Area Of Specialization Using Neural Network

Prediction is one of the unique capabilities of neural network technology. This approach can be used in any area where knowledge is highly structured and can be
represented in patterns. Neural networks have been used as a mechanism for a lot of industries such as in education, businesses, finance, banking, medicine, space science, marketing and others. A lot of real problems that can be predicted in order to obtain the most effective decision-making in the future. The objective of this study is to evaluate neural network techniques in predicting the area of specialization of Bachelor in Information Technology (B.I.T.) students at Universiti Utara Malaysia (UUM). In order to gain the best performance of the data, the method used is supervised learning. The study covers a brief discussion on the neural network concepts, the methodology used and the area of specialization dataset as a case study and allso including a brief discussion on supervised learning. The development of application involves data collection and management, then followed by neural network simulator for training and testing. The data used for training and testing the network was provided by Sekolah
Teknologi Maklumat, Universiti Utara Malaysia. The best network model produced a prediction accuracy of 95.79 %. This clearly shows that neural network has a potential to be used for building education decision support system.