The aim of research paper is to improve the current
trends in the higher education systems to understand from the
outside which factors might create loyal students. The necessity
of having loyal students motivates higher education systems to
know them well, one way to do this is by using valid
management and processing of the students database. Data
mining methods represent a valid approach for the extraction
of precious information from existing students to manage
relations with future students. This may indicate at an early
stage which type of students will potentially be enrolled and
what areas to concentrate upon in higher education systems for
support. For this purpose the data mining framework is used
for mining related to academic data from enrolled students.
The rule generation process is based on the decision tree as a
classification method. The generated rules are studied and
evaluated using different evaluation methods and the main
attributes that may affect the student’s loyalty have been
highlighted. Software that facilitates the use of the generated
rules is built using VB.net programming language which allows
the higher education systems to predict thestudent’s loyalty
(numbers of enrolled students) so that they can manage and
prepare necessary resources for the new enrolled students.