APPLICATION OF CLUSTER ANALYSIS FOR IDENTIFICATION OF VARIABLES ASSOCIATED WITH ACADEMIC SUCCESS OF HIGHER EDUCATION STUDENTS
Universidad Autónoma de Sinaloa (MEXICO)
About this paper:
Appears in: ICERI2012 Proceedings
Publication year: 2012
Conference name: 5th International Conference of Education, Research and Innovation
Dates: 19-21 November, 2012
Location: Madrid, Spain
Abstract:Nowadays, higher education institutions in Mexico are facing two major problems, the high desertion rate and low terminal efficiency rate. These indicators have a negative influence in these institutions, creating problems such as low uptake of funds, difficulties for the accreditation of its educational programs, among many others.
In this research, we analyze the data collected from academics paths studies and supported by software in order to find viable information to identify the factors that affect the academic success of students in higher education and that offers an efficient strategy for the efficient selection of candidates to study in the college to avoid in this way desertion and increasing terminal efficiency rate.
In this sense, we apply the techniques of data mining, cluster analysis, using the clustering algorithm known as k-means, which is to group items into homogeneous groups based on similarities or similarities between them. We used SPSS (Statistical Package for Social Sciences) for the implementation of k-means algorithm, in order to analyze the statistics of academic paths that were extracted from a graduated group of higher education. Starting with a sample extracted from graduated students in computer science from the Computer Science Faculty of Mazatlan (Autonomous University of Sinaloa), with the help of their overall performance and analyzing qualitative and quantitative factors such as their age, gender, high school average, parents’ education, family income, marital status, former high school, among others; and discarding those that, according to mathematical analysis, do not affect student performance.
The results show that this technique of unsupervised clustering and hierarchical able to identify the relevant variables associated with academic success and successfully classify the two groups (successful students and students with low academic performance).
We hope this study will serve as a tool for selecting students to study computer science, as well as a tool for diagnosis and prediction of academic performance.
Keywords: Data Mining, Cluster Analysis, K-means Algorithm, Higher Education, Academic Success, Academic Paths, and Computer Science.