Predicting Students’ Marks in Hellenic Open University Sotiris B. Kotsiantis & Panayiotis E. Pintelas Educational Software Development Laboratory Department of Mathematics University of Patras {sotos, pintelas}@math.upatras.gr Abstract The ability to provide assistance for a student at the appropriate level is invaluable in the learning process. Not only does it aids the student’s learning process but also prevents problems, such as student frustration and floundering. Students’ key demographic characteristics and their marks in a small number of written assignments can constitute the training set for a regression method in order to predict the student’s performance. The scope of this work compares some of the state of the art regression algorithms in the application domain of predicting students’ marks. A number of experiments have been conducted with six algorithms, which were trained using datasets provided by the Hellenic Open University. Finally, a prototype version of software support tool for tutors has been constructed implementing the M5rules algorithm, which proved to be the most appropriate among the tested algorithms. 1. Introduction The application of Machine Learning Techniques in predicting students’ performance proved to be helpful for identifying poor performers and it can enable tutors to take remedial measures at an earlier stage, even from the very beginning of an academic year using only students’ demographic data, in order to provide additional help to the groups at risk [4]. The diagnosis of students’ performance is increased as new curriculum data is entered during the academic year, offering the tutors more effective results. It was showed in [4] that the most accurate machine learning algorithm for identifying predicted poor performers is the Naïve Bayes Classifier. However, that work could only predict if a student passes a course module or not. This paper uses existing regression techniques in order to predict the students’ marks in a distance learning system. It compares some of the state of the art regression algorithms to find out which algorithm is more appropriate not only to predict student’s performance accurately but also to be used as an educational supporting tool for tutors. For the purpose of our study the ‘informatics’ course of the Hellenic Open University (HOU) provided the data set. Generally, the usage of regression analysis to classify data can be an extremely useful tool for researchers and Open University administrators. A plethora of data can be utilized simultaneously to classify cases and the resultant model can be evaluated for usefulness relatively easily. The ability to develop a predictive model based on the model produced through the regression analysis procedure increases its usefulness substantially. Open Universities can utilize this dynamic and powerful procedure to target services and interventions to students who need it most, thereby utilizing their resources more effectively. The following section describes in brief the Hellenic Open University (HOU) distance learning methodology and the data of our study. Some very basic definitions about regression techniques are given in section 3. Section 4 presents the experiment results for all the tested algorithms and at the same time compares these results. Section 5 presents the produced educational decision support tool. Finally, section 6 discusses the conclusions and some future research directions. 2. Hellenic Open University and Data Description The mission of the Hellenic Open University (HOU) is to offer university level education using the distance learning methodology. The basic educational unit of the HOU is the course module (referred simply as module from now on) that covers a specific subject in graduate and postgraduate level. For the purpose of our study the ‘informatics’ course provided the training set. A total of 354 instances (student’s Proceedings of the Fifth IEEE International Conference on Advanced Learning Technologies (ICALT’05) 0-7695-2338-2/05 $20.00 © 2005 IEEE