I. a lot of data about students. Understanding

                                                                                                                                                           I. Introduction

When evaluating an institution’s quality graduation rate
has become one of the most important indicators. This is mainly due to several types
of research that have shown the benefits of having a college degree to
individuals and the society. A higher education report (1) gave a detailed
evidence of the benefits of public and private post-secondary education in
which it stated that college graduates are more likely to be satisfied with
their jobs and place a greater importance on the job they do. Individuals with
a college degree are more likely to engage civilly with others and have higher
rates of participation in volunteering and voting (2). Data from the United States
Department of labor (3) showed that an increase in education attainment showed
increase in earnings and decrease in unemployment.  Increasing student degree college degree is
important to the economic health of the United States.

Your time is important. Let us write you an essay from scratch
100% plagiarism free
Sources and citations are provided


Get essay help

Over the years there has been an increase in the number of
higher education institutions and graduates produced by them every year.
Institutions work hard to follow new teaching methods and practices, but they
are still met with the problem of student’s poor performance and eventual
dropping out of school.

Every year universities generate and store a lot of data
about students. Understanding and analyzing the data can help predict factors
that lead to students dropping out which could be vital in any decision and
policy making that may help improve the performance of students and the
graduation rate of the college.

Students drop out of a higher institution for a number of
reasons. Some of the reasons include; lack of finances, change of academic
goal, dissatisfaction with the academic environment, student’s inability to
assimilate or manage normal work, lack of motivation, job demands, and incompatible
with campus values (5). One study indicated that students’ academic, social and
cultural integration in the university setting was a major determinant of
student retention (6).

Predicting the factors of low performance at an early
stage can help universities take proactive actions in improving the performance
of students that may be susceptible to dropping out. This is positive for all
parties involved. Students will be able to identify their weaknesses and work better
to improve areas that need work. Teachers will be able to concentrate more on
students who require more attention and plan their lectures to accommodate such
students. Parents will be reassured that their children are getting the
assistance they need to do well. Management can start new policies or update
existing ones to include better strategies that will improve the performance of
students. Ultimately all these will help in producing capable workforce and
lead to a sustainable growth for the country.

Data mining techniques are being applied to the field of
education to investigate scientific questions within educational research and
it is called educational data mining (also referred to as “EDM”).  Datamining analyses data from different aspects
and outlining the results as a useful information.  It involves making discoveries within the
unique kinds of data by identifying novel, valid, understandable and
potentially important patterns in data (4).

Data mining can be a very effective tool in revealing
hidden patterns and insights about education data that may the difficult to
find and comprehend with the use of statistical methods.

The purpose of this study was to use datamining techniques
to predict factors that influence graduation rates using data driven
information that considered the student’s population and educational
characteristics. Other studies on graduation rates have used statistical
methods and the ones that used data mining just looked at pre-enrollment
characteristics.