Journal of Theoretical and Applied Information Technology
28
th
February 2018. Vol.96. No 4
© 2005 – ongoing JATIT & LLS
ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195
875
CLUSTERING FAILED COURSES OF ENGINEERING
STUDENTS USING ASSOCIATION RULE MINING
ROSEMARIE M. BAUTISTA
Associate Professor, Bulacan State University, College of Information and Communications Technology,
Philippines
Email: rosemarie.bautista@bulsu.edu.ph
ABSTRACT
In today’s world, the fast-paced changes in technology and upswing volume of organizational data in
almost all domains including academe are very remarkable. This coupled with the aspiration to gain
competitive advantage necessitate the utilization of data mining. This paper applies the processes in the
Knowledge Discovery in Databases by Fayyad and presents in methodological way the steps performed
towards finding the associations between courses failed by engineering students. It started with the
preparation of data moving towards proper transformation of it for data mining and concluding with data
interpretation and evaluation. Using association rule mining through Apriori algorithm, the rules were
extracted from the database. The statistical significance and the strength of the rule were analyzed using 3
measures of usefulness: lift, support and confidence. All the rules generated have positive co-relation, that
is, the relationships of the consequent of the rule with the antecedent are not due to chance. The over-all
output of the study is expected to offer viable results that may be used by administrator, academic advisor
and curriculum planners in devising worth-while strategies such as improvement of teaching methodology,
re-structure of curriculum, modification of course pre-requisites or development of supplemental activities
to students.
Keywords: Data Mining, Association Rule Mining, Market Basket Analysis, Knowledge Discovery in
Databases, Educational Data Mining
1. INTRODUCTION
The hasty growth of technology and the surge
of enormous data are increasingly evident in the
past few decades. The widespread computerization
and explosive growth of data in almost every
conceivable field including government,
businesses, recreations, education and others
necessitate the need to analyze, manage and
transform such data into usable information. Data
mining, thus, becomes an imperative approach in
these integral tasks [1].
Data mining or DM which is usually referred
to as the process of discovering invaluable
knowledge from databases [2], [3] is part of the
natural evolution of information technology [1]. It
oftentimes uncovers hidden patterns which are not
usually generated by traditional computer-based
information system. It is termed as educational
data mining or EDM in the context of education.
EDM is now gaining popularity and capturing the
interest of countless researchers who wish to extract
previously unknown patterns and unique
information from educational databases [4], [5]. It
is used to analyze students’ historical attributes to
gain understanding of some academic records,
enrolment data, student behavior and pedagogical
performance that may improve decision-making
and better management of scholastic-related issues
[6], [7], [8]. Techniques such as association rule, k
means and some classification algorithms were
used to analyze both students’ behavior and
teachers’ performance to provide recommendation
for further curriculum improvement [9].
Among the thrust of almost every university is
continuous quest for excellence which may be done
by constant revisit of curriculum. The Bulacan
State University (BulSU) shares the same
unwavering commitment. One of its prides is the
College of Engineering (COE) however also
considered one of those with the highest students’