Optimation of Social Assistance Recipient Determination Using K-Means Clustering Algorithm and K-Nearest Neighbour Algorithm
Abstract
Determining the status of the family as recipients of assistance is very important, so that aid can be distributed accurately. Data mining takes advantage of experience or even mistakes in the past to add quality based on examples as well as the results of the analysis, one of which uses the capabilities of data mining techniques, namely clustering & classification. The purpose of this research is to determine the right beneficiaries. K-Means Clustering and K-Nearest Neighbor are 2 data mining problem solving algorithms used in selecting beneficiaries. Both of these troubleshooting algorithms make good performance. However, to be widely used, it is necessary to research which algorithm has higher accuracy. Based on this, in this study a comparison of the K-Means Clustering and K-Nearest Neighbor algorithms was carried out on the problem of selecting beneficiaries. Comparisons were made using 1760 data. Based on the tests that have been carried out, beneficiaries using k-means clustering got as much as 65.145% while K-Nearest Neighbor as much as 99.6501%. This shows that the K-Nearest Neighbor problem solving algorithm has higher accuracy.
Downloads
References
Adinugroho, S., & Sari, Y. A. (2018). Implementasi Data Mining Menggunakan WEKA (Edisi Pert). UB Press.
Bhagya, T. G., & Prakarsa, G. (2020). Model Keputusan Penentuan Jenis Distribusi Dari Kerusakan Bearing pada Mesin TFO di PT XYZ. SISINFO: Jurnal Sistem Informasi dan Informatika, 2(2). 134-142.
Eric Fammaldo, L. H. (2018). Penerapan Algoritma K-Means Clustering Untuk Pengelompokan Tingkat Kesejahteraan Keluarga Untuk Program Kartu Indonesia Pintar. V (1), 23–31
Hafidz, C. A. H. R. A. H. I. (2012). Clustering Kelompok Swadaya Masyarakat (KSM) dalam Menentukan Kebijakan Bantuan Badan Pemberdayaan Masyrakat di Kota Surabaya dengan. 1(1).
Hasanah, R. L., Hasan, M., & Pangesti, W. E. (2019). Klasifikasi Penerima Dana Bantuan Desa Menggunakan Metode KNN (K-Nearest Neighbor). 16 (1), 1–6.
Hermawati, F. A. (2013). Data Mining (P. Christian (ed.)). ANDI.
Isyarah, F., Hasan, A., Wiza, F., Studi, P., Informatika, T., Ilmu, F., Universitas, K., Penduduk, J., Sekolah, L., & Kerja, A. (2020). Clustering Daerah Miskin Di Provinsi Riau Menggunakan Metide K-Means. 1 (1), 1–12.
Jajam Haerul Jaman, S. A. F. (2019). Klasifikasi Calon Mahasiswa Bidikmisi dengan Algoritma K-Nearest Neighbor. Prosiding Annual Research Seminar, 5(1), 1–5.
Kusanti, J., & Sutanto, D. (2021). Journal of Computer Networks , Architecture and High Performance Computing Combination of Decision Tree and K-Means Clustering Methods for Decision Making of BLT Recipients in the Covid-19 Period Journal of Computer Networks , Architecture and High Perfor. 3(1), 80–88.
Li, Y., & Wu, H. (2012). 2012 International Conference on Solid State Devices and Materials Science A Clustering Method Based on K-Means Algorithm. Physics Procedia, 25, 1104–1109. https://doi.org/10.1016/j.phpro.2012.03.206
Noviana, T., Jasmir, J., & Novianto, Y. (2019). Penerapan Data Mining Menentukan Kelompok Prioritas Penerima Bantuan Beras Rastra Dengan Clustering K-Means. Program Studi Teknik Informatika, Stikom Dinamika Bangsa, 159–174.
Permana, A. D., Nasution, V. M., & Prakarsa, G. (2020). Design and Development of Fuzzy Logic Application Tsukamoto Method in Predicting the Number of Covid-19 Positive Cases in West Java. 1(2), 85–95.
Prasetyo, E. (2014). Data Mining Mengolah Data Menjadi Informasi Menggunakan Matlab (A. Sahala (ed.)). ANDI.
Soeleman, D. M. C. A. S. M. A. (2019). Penentuan Prioritas Penerima Dana Bantuan Operasional Pendidikan Lembaga Pendidikan Anak Usia Dini dengan Metode. JUrnal Teknologi Informasi, 15(2), 77–92.
Suara.com. (2020). BKKBN Sebut Dua Anak Lebih Sehat untuk Keluarga Indonesia.
https://www.suara.com/health/2020/09/28/142855/bkkbn-sebut-dua-anak-lebih-sehat-untuk-keluarga-indonesia-apa-sebabnya?page=all
Yani, S., Jumeilah, F. S., & Kadafi, M. (2020). Algoritma K-Nearest Neighbor Untuk Menentukan Kelayakan Keluarga Penerima Bantuan Pangan Non Tunai (Studi Kasus: Kelurahan Karya Jaya). Journal of Information Technology Ampera, 1(2), 75–87. https://journal-computing.org/index.php/journal-ita/index
Yogachi, E. F., Nasution, V. M., & Prakarsa, G. (2021). Design and Development of Fuzzy Logic Application Mamdani Method in Predicting The Number of Covid-19 Positive Cases in West Java. IOP Conference Series: Materials Science and Engineering, 1115(1), 012031. https://doi.org/10.1088/1757-899x/1115/1/012031
