Clustering the number of unemployed individuals in North Sumatra using the K-Means and K-Medoids algorithms.

Abstract

Unemployment is a major issue in developing countries, and one of them is North Sumatra Province. The mismatch between the number of job seekers and available job opportunities is one of the main causes of the high attrition rate in this area. This unemployment problem has a major impact on society, including increasing crime, social conflict and poverty. Therefore, this research aims to analyze poverty levels based on districts/cities in North Sumatra Province using the K-Means and k-medoids algorithms, with a focus on the Diploma III and S1 education level variables. In this research, to group the number of unemployed, data is needed, and the data in this research was obtained based on the Central Statistics Agency of North Sumatra Province in the field of work energy, the data that will include is the average of the data on the number of unemployed for 2017-2022. This research identifies two main groups of poverty in North Sumatra Province through the use of the K-Means and K-Medoids algorithms. Through testing using the K-Means and K-Medoids algorithms, two main clusters were identified, where Cluster 2 includes the city of Medan. The second algorithm provided similar conclusions regarding higher poverty rates in the city. These results show consistency in identifying areas with reduced poverty, but in the K-

Means algorithm it produces 2 cities and in the k-medoids algorithm it produces 1 city. This research reveals that this level of poverty especially impacts individuals with Diploma III and S1 education. Data analysis suggests that high poverty rates in this group may be due to a mismatch between labor market needs and the educational qualifications possessed by individuals. The results of this research have important implications for policy makers and decision makers in efforts to reduce poverty levels in North Sumatra Province. Recognizing the differences between these poverty groups can help in planning more effective training and skills development programs, as well as developing employment opportunities that match the educational qualifications of local people.