A proposed academic advisor model based on data mining classification techniques

University and higher institute admission are an intricate decision process and it is an important responsibility of the students to select the correct study track. The increase of the student's major dropout rate in higher education systems is one of the important problems in most institutions. One approach to solve such problem and succeed in academic life is to help the students in selecting a suitable major and assign them to the right track. The objective of our research is to build academic advisor model to students for their higher education which utilize classification data mining for recommending the suitable academic major. The method applied in the research is data mining classification techniques through decision tree method for advising students to select suitable major and help assign them to the right track. The proposed model classifies students and matches them to the proper study tracks according to their features. The three decision tree classification algorithms, namely J48, random tree and reduces error pruning (REP) tree was first applied to real data in a managerial higher institute in Giza Egypt and results are compared between them. Finally, the results showed that J48 algorithm gives 16 rules and we eliminate the rules that give low CGPA and we will use the 5 better rules that have the highest CGPA based on CGPA grade that equal (A) and J48 algorithm gives the highest accuracy 87.64% and classification error was 12.36% and was thus selected as the main classifier for building the proposed model based on the rules that we obtained from J48 algorithm than the two other classification algorithms and thus suggest using the generated J48 decision tree in our proposed student advising model to enhance students' academic performance and decrease dropout.