UTILIZATION OF K-MEANS CLUSTERING METHOD IN GROUPING DATA ON PARENTS’ INCOME OF STMIK DHARMAPALA RIAU STUDENTS

Abstract

Not a few children in Indonesia who drop out of continuing their education because one of the causes is family economic factors, insufficient parental income and not balanced with the number of dependents in the family, therefore researchers conducted a survey with questionnaires to students at STMIK Dharmapala Riau in order to determine the variables of grouping student parents' income data, in order to determine the economic level of students with the category of able and less able to use K-Means Clustering method assisted by data processing using the Rapidminer 5.3 application. The data criteria used in this method include the last student achievement index, father's job, mother's job, the amount of income of father and mother in one month and the number of dependents in the family. The K-Means Clustering method is one method to group data based on its characteristics, so that data that has the same characteristics are grouped in the same cluster and data that has different characteristics are grouped in another cluster. The resulting clusters are categorized as capable and underprivileged, which can be useful in making decisions.