Student performance analysis using clustering algorithm

University and technical organizations are facing high competition and their challenge is in analyzing their performance. The major challenges are in admission, student placement and in the curriculum. The two most important process during which data's are collected and analyzed are admission and placement. The ranking of the university depends on academic performance and placement of the student. Apart from academic performance there are various other factors which help in understanding the overall performance of the student. In this research work, the data mining technique is used to understand the performance of student and group the students under various categories as a student need to consistently improve to compete in today's world.

I. Introduction

Information and Technology era has led to collection of volumes of information. These collected information has to be converted to useful form for better decision making. In any university/higher institution there are volumes of student data like attendance, marks etc. These data can be qualitatively and quantitatively analyzed using data mining techniques. Performance analysis plays a very important role in higher institutions and student mark or grade is an important factor. The most important parameter that is used to judge a student performance in the college are marks. The other parameter like projects completed, internships and skill set also play a vital role in employment opportunity for a student. Students should not be grouped only on the basis of marks they have been scoring and ignoring their extracurricular performance. Therefore, grouping of students based on these parameters is required to obtain a comprehensive view of the performance of the student and simultaneously ascertain details from their time to time performance. This paper is focused on the implementation of a data mining technique and a method for acquiring student overall performance during their entire term. The research works uses K-means clustering algorithm for categorizing students in different clusters. It will also help the students and teachers to focus on improvement strategies by way of monitoring the performance of the student.