Student Performance Prediction Model using Machine Learning Approach: The Case of Wolkite University (original) (raw)

A high prediction accuracy of the students' performance is helpful to identify the low performance students at the beginning of the learning process. Machine learning is used to attain this objective. Machine learning techniques are used to discover models or patterns of data, and it is helpful in the decision-making. The ability to predict performance of students is very crucial in our present education system. We applied Machine learning concepts for this study. The dataset used in our study is taken from the Wolkite university registries office for college of computing and informatics from 2004 up to 2007 E.C with respect to each department. In this study, we have been collected student's transcript data that included their final GPA and their grades in all courses. After pre-processing the data, we applied the machine learning methods, neural networks, Naive Bayesian and Support Vector Machine (SMO). Finally, we built the model for each method, evaluate the performance and compare the results of each model. Using machine learning, the aim was to develop a model which can derive the conclusion on students' academic success. I. INTRODUCTION For higher education institutions whose goal is to contribute to the improvement of quality of higher education. The quality of higher education institutions implies providing the services, which most likely meet the needs of students, academic staff, and other participants in the education system. Tekeste writes " The golden age of modern education in Ethiopia " is usually dated to the years between 1941 and 1970 (the regime of HIM Hailesellassie). Education was free and it applied more to the poorer section of the population; the rich and the aristocracy were less enticed by the economic returns of education [1][7]. Currently, the Ethiopian Government gives higher education a central position in its strategy for social and economic development. Ethiopia has radically expanded the numbers of its higher education institutions: from two Federal universities to 33; among this 10 of them are opened before 5 years and one of this is Wolkite University. Nowadays, the data base that store data and information for organization becomes complicated and difficult to analysis [2]; for this case we are going to apply Machine Learning techniques to resolve those problems. Wolkite University has its own student management information system that was developed by Bahir Dar University Course and Curriculum Management System. However, this database contains so much data that it becomes almost impossible to manually analyze them for valuable decision-making information. In order to analysis this complex data base we can able to use machine learning techniques. This Study conducted in 993students from college of computing and informatics within Wolkite University with respective departments. We were using WEKA open source software to test the prediction of the student performance. It provides many different algorithms for data mining and machine learning. WEKA is open source and freely available. It is also platform-independent[3] .We may have various factors for education with in Wolkite University such as environment, family standard of each student, gender, teacher's educational background and education policy[1][4][5], but our research is not going through each factor because it is physiological factor instead of learning once. This study has the following contributions.