Data Mining Applications in Higher Education and Academic Intelligence Management

Higher education institutions are nucleus of research and future development acting in a competitive environment, with the prerequisite mission to generate, accumulate and share knowledge. The chain of generating knowledge inside and among external organizations (such as companies, other universities, partners, community) is considered essential to reduce the limitations of internal resources and could be plainly improved with the use of data mining technologies. Data mining has proven to be in the recent years a pioneering field of research and investigation that faces a large variety of techniques applied in a multitude of areas, both in business and higher education, relating interdisciplinary studies and development and covering a large variety of practice. Universities require an important amount of significant knowledge mined from its past and current data sets using special methods and processes. The ways in which information and knowledge are represented and delivered to the university managers are in a continuous transformation due to the involvement of the information and communication technologies in all the academic processes. Higher education institutions have long been interested in predicting the paths of students and alumni (Luan, 2004), thus identifying which students will join particular course programs (Kalathur, 2006), and which students will require assistance in order to graduate. Another important preoccupation is the academic failure among students which has long fuelled a large number of debates. Researchers (Vandamme et al., 2007) attempted to classify students into different clusters with dissimilar risks in exam failure, but also to detect with realistic accuracy what and how much the students know, in order to deduce specific learning gaps (Piementel & Omar, 2005). The distance and on-line education, together with the intelligent tutoring systems and their capability to register its exchanges with students (Mostow et al., 2005) present various feasible information sources for the ...