Proceedings of the International Soft Science Conference 2012(ISSC2012), 06-08 November, 2012 Phnom Penh City, Cambodia Paper No. 63-69 63 SURVEY OF CLASSIFICATION METHODS FOR ACADEMIC PERFORMANCE EVALUATION Fadzilah Siraj 1* , NurAzzah Abu Bakar 2 , Md. Rajib Hasan 3* , MegatFirdaus Haris 4 &Siti Farina Zakria 5 1* Universiti Utara Malaysia, Malaysia, fadzilahsiraj@gmail.com 2 Universiti Utara Malaysia, Malaysia, nurazzah@uum.edu.my 3* Universiti Utara Malaysia, Malaysia, mrhuum@live.com 4 Universiti Utara Malaysia, Malaysia, s808208@student.uum.edu.my 5 Universiti Utara Malaysia, Malaysia, s813143@student.uum.edu.my *Corresponding Author CORRESPONDING AUTHOR: For all stages of refereeing and publication including post- publication ABSTRACT. Classification is a data mining technique used to predict group membership for data instances. Educational data mining is an emerging field that deals with the use of data mining techniques on the data related to the field of education. For higher educational institutions, the success of creation of human capital is the subject of a continuous analysis. To date, higher edu- cational organizations are placed in a very high competitive environment and to remain competitive, organizations need better assessment, evaluation, planning, and decision making. As such, classification modelling for academ- ic performance for the graduates could provide some insight to the university in order to take necessary information for improving the students’ academic performance. Hence, the goal of this survey is to provide the review of differ- ent classification techniques that have been used in educational field, in par- ticular those with regard to evaluation of students’ academic performance. In this paper three classification techniques are presented including Bayesian network, Neural Network and K-nearest Neighbour. Keywords: Classification, Data Mining, Bayesian Network, Neural Network, K-nearest Neighbour INTRODUCTION Classification is a data mining (DM) technique used to predict group membership for data instances(Lee &Mangasarian, 2001). These techniques have been applied in a great number of fields including bioinformatics, retail sales, counter-terrorism, stock market, real estate, cus- tomer relationship management, engineering, medicine, web mining and others. Each tech- nique differs in terms of complexity and power, and provides different model for different use. It applies modern and statistical computational technologies in its quest to expose useful pattern hidden within the large databases (Siraj&Abdoulha, 2011).An example of classification method in DM is illustrated in Figure 1. Figure 1: Classification Method in Data Mining