Student Orientation Recommender System using TOPSIS and AHP

Abstract

The process of traditional school guidance is carried out by specialists. They make astudy of the student files based on the marks of the first year and the second year ofthe baccalaureate. Considering the progressive number of students and also the lack oftime to make the decision, as the selection of the specialty has a great effect on theacademic course of the students, we have realized a system of specialtyrecommendation, to computerize the orientation process and save time. But the majorproblem is that the students do not care about this process and pay no attention to itdespite its importance. As well as the software which makes the orientation ischargeable.To order these specialties to take the best specialty. We have arrived at aproblem of multi-criteria which makes it impossible to make a decision with thesecriteria. Because these criteria do not have the same importance and also are notcompatible, as there are criteria that must be maximum and other criteria must beminimal. To solve this problem, two systems of orientation and academicreorientation of students have been implemented. In both systems, the SMOTEmethod has been used to balance the learning data in the preprocessing phase. Then inthe treatment phase, we sorted the specialties using in the first system, a hybridizationof TOPSIS method and the information gain to find the weights of the criteria used,and in the second system, we used a hybridization of the AHP method andinformation gain. The results obtained indicate that before balancing data using the SMOTE method, the total accuracy of TOPSIS (84.20%) is higher than the total accuracy of AHP (83.71%). After applying balancing data using the SMOTE method,the total accuracy has increased. The total accuracy of TOPSIS (91.35%) is alsohigher than the total accuracy of AHP (90.83%). For the complexity of the twomethods, it is related to the number of criteria and the number of alternatives. If thenumber of criteria is more than 10 criteria, the complexity of TOPSIS is less than thecomplexity of AHP, and vice versa. The complexity of the two methods also dependson the number of alternatives, if the number of alternatives exceeds 10, the TOPSISmethod becomes more complex than the AHP method. In general, the system basedon TOPSIS method and the information gain is more precise than the system based onthe AHP method and the information gain. But the complexity of the AHP method isless than the complexity of the TOPSIS method.