PENERAPAN ALGORITMA K-NEAREST NEIGHBOR (KNN) UNTUK KLASIFIKASI CALON PENERIMA BIDIKMISI

  • Siti Julaiha Alumni Program Studi Teknik Informatika
  • Martaleli Bettiza Dosen Fakultas Teknik UMRAH
  • Dwi Amalia Purnamasari Dosen Fakultas Teknik UMRAH
Keywords: Data Mining, Classification, Bidikmisi, K-Nearest Neighbor

Abstract

Raja Ali Haji Maritime University has selected scholarships for students, one of which is the Bidikmisi program. Bidikmisi is assistance provided by the government to students who are lacking in economic terms who have achievements in all tertiary institutions in Indonesia. Based on the data of 2019 UMRAH bidikmisi students, students who register for Bidikmisi exceed the specified quota limits so there is a need for a classification so that the bidikmisi assistance provided is correct target. This research was conducted to classify prospective bidikmisi recipients using the K-Nearest Neighbor (KNN) algorithm. The data used in the study were 414 data with 331 as training and 83 as testing. This study also uses the parameters of the parents 'occupation, parents' income, dependents, residence, electricity costs, and test scores. The stage carried out in this research is weighting the data then calculating according to the KNN algorithm. Based on the results of tests carried out with k = 5, the accuracy results are 83.13%, the precision is 82.35%, the recall is 89.36%.

Published
2021-10-12
Section
Teknik Informatika