Implementation of Data Mining Algorithms for Grouping Poverty Lines by District/City in North Sumatra
Mhd Ali Hanafiah, Anjar Wanto
Abstract
The poverty line is useful as an economic tool that can be used to measure the poor and consider socio-economic reforms, such as welfare programs and unemployment insurance to reduce poverty. Therefore, this study aims to classify poverty lines according to regencies/cities in North Sumatra Province, so that it is known which districts/cities have high or low poverty lines. The grouping algorithm used is K-Means data mining. By using this algorithm, the data will be grouped into several parts, where the process of implementing K-Means data mining uses Rapid Miner. The data used is the poverty line data by district/city (rupiah/capita/month) in the province of North Sumatra in 2017-2019. Data sourced from the North Sumatra Central Statistics Agency. The grouping is divided into 3 clusters: high category poverty line, medium category poverty line, and the low category poverty line. The results for the high category consisted of 5 districts/cities, the medium category consisted of 18 districts/cities and the medium category consisted of 10 districts/cities. This can provide input and information for the North Sumatra government to further maximize efforts to overcome the poverty line in the area.