PENERAPAN ALGORITMA K-NEAREST NEIGHBOR DALAM KLASIFIKASI DATA HASIL PRODUKSI KELAPA SAWIT PADA KUD TIRTA KENCANA

Abstract

KUD Tirta Kencana is located in Air Emas Village, Singingi Subdistrict, Kuantan Singingi Regency, Riau, assisting the processing of oil palm plantations owned by its citizens for the development of the economy in the Air Emas Village. KUD Tirta Kencana consists of 17 Farmers Groups.The data processing system in KUD TirtaKencana still uses conventional recording where the palm oil production data of each farmer group is recapitulated into Ms. Excel, so the data entered into Ms. Excel is increasingly piling up and irregular, which makes data difficult to understand and the lack of information that can be used for the development of KUD TirtaKencana in the field of palm oil production in the future.With this, it is necessary to analyze and process the data of palm oil production in KUD Tirta Kencana using data mining calculation techniques, one of the algorithms contained in the data mining technique is the k-Nearest Neighbor (k-NN) algorithm. This algorithm is a method that uses a supervised learning algorithm, where the results of the new test sample are classified based on the majority of the categories in k-NN.From this research, it is known that the similarity of production yields among farmer groups, thus it can be predicted that the yield of palm oil production in the future, revolves around the relationship between the similarity of production between farmer groups based on their respective clusters. The test results using the values ​​of K = 2, K = 3, and K = 4, have an accuracy value of K = 2 and K = 3 that is 85.71%, for K = 4 produces an accuracy value of 71.43%.