Academic evaluation is an important process to know how well the learning process was conducted and also one of the decisive factors that can determine the quality of the higher education institution. Though it usually curative, the preventive effort is needed by predicting the performance of the student before the semester begin. This effort aimed to reduce the failure rate of the students in certain subjects and make it easier for the PBL tutor to create appropiate learning strategies before

more »

... he tutorial class begin. The purpose of this work is to find the best data mining technique to predict student academic performance on PBL system between two data mining classification algorithms. This work applied and compared the performance of the classifier models built from Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). After preprocessed the dataset, the classifier models were developed and validated. The result shows that both algorithms were giving good accuracy by 97% and 95,52% respectively though SVM showing the best performance compared to KNN in F-Measure with 80%. The further deployment is needed to integrate the model with academic information system, so that academic evaluation can be easily done. 1. Introduction Problem Based Learning (PBL) is a learning methodology that encourages students to better understand the subject being studied. This learning system combines the basic knowledge and skill by positioning the student as a problem solver to the problems that will be faced by the student in the future [1]. In PBL system, students are directed to think of solving the problems based on a real case problem that is then discussed together with the peers in a small group discussion. The effectiveness of the PBL implementation depends on three main areas: clinical cases discussed, the performance of the tutor and the performance of the students [2]. So with this learning model, if the student performance is the output indicating the effectiveness of the learning process, then the collaboration of these three factors will be the main determinant of the success of PBL learning process. The academic evaluation process should also be focused on these factors. Academic evaluation is one of the essential things applied by universities to know the quality of the learning process. Academic evaluation is also one of the decisive factors assessed in the accreditation process. Implementation of academic evaluation is usually conducted at the end of each semester which results are then used to improve academic quality in the following semesters. So that the evaluation is usually curative. Preventive efforts should then be undertaken to predict student performance early so that appropriate learning strategies can be formulated before the semester begins. Preventive efforts also aim to reduce the failure rate of students in certain subjects. Currently, many techniques have been proposed to predict student academic performance, including data mining techniques. Data mining is now a popular technique used in education which is then referred to as Educational Data Mining (EDM). EDM is an area of research that integrates several fields of science conducted to develop a method for analyzing a large amount of data. The main purpose of EDM is to find hidden knowledge and pattern to improve student performance in learning [3]. Data mining approach to predict student academic