Abstract
Data mining methods are often implemented at various sectors today for analyzing available data and extracting information and knowledge to support decision-making. Educational data mining is an emerging discipline, concerned with developing methods and algorithms that discover knowledge from data originating from educational environments. This paper study the application of data mining methods, namely classification and clustering, on undergraduate Information Technology student's data in a blended-learning university. A classifier that implements a decision tree algorithm is used to predict student performance at the end of the program based on students' socio-demographic variables and achieved results from the first (i.e. preparatory) year of the study program. The classifier is also used to derive critical courses that can serve as indicators for students' performance. A clustering algorithm, on the other hand, is applied for identifying the attributes of withdrawn students from this degree program. The results reveal the high potential of data mining applications in providing insights for students, academic advisors and university management, which can help in improving the quality of the educational processes and enhancing learning experience.