Application of Data Mining to Predict Birth Rates in Medan City Using the K-Nearest Neighbor Method
Abstract
The birth rate of babies in Indonesia tends to increase every month, based on this fact, the population in Indonesia is increasing over time. One of the contributing factors is increasingly sophisticated technology, so that a country's birth rate can be accelerated, and if this event occurs continuously it will have an impact on population density which will occur notlonly inlIndonesia, butlalso throughoutylthelworld. Therefore, birth rate predictions are needed for planning and public policy in the fields of health and social welfare. One of them is using data mining techniques to predict the number of births in Medan City using the KNN method. KNN is a classification method based on the neighborhood value between training data and test data. Thelpredictioniresults will beicompared withlactual datalto measure thekaccuracy of predictions on birth data totaling 131 data. The accuracy results obtained were 83.9% with a total of 4,413 births and 8,485 pregnant women
Keywords
Full Text:
PDFReferences
Idris, M. (2020). Implementasi-Data Mining-Dengan AlgoritmaaNaïve Bayess Untuk Memprediksi TKP- Kriminalitas Di KabupatennPonorogo. Paper Knowledge . Toward a Media History of Documents, 7(1), 1–33.
Indahsari, D. K., & Kurniawan, Y. I. (2019). AplikasiiPrediksi Usia KelahirannDengan Metode K-NearestNeighbor. Jurnal Kebidanan, 11(01), 1. https://doi.org/10.35872/jurkeb.v11i01.335
Novrizaldi. (2021). Hasil Surveii Penduduk 2020 Peluang Indonesia Maksimalkann-Bonus Demografi. KEMENKO-PMK. https://www.kemenkopmk.go.id/hasil-survei-penduduk-2020-peluang-indonesia-maksimalkan-bonus-demografi
Parihah, N. I., Hartini, S., & Siregar, J. (2020). Prediksi_Angka KelahirannBayi Pada Desa ATridaya Saktii Dengan Menggunakan Algoritmaa NaiveBayes. Journal of Students‘ Research in Computer Science, 1(2), 77–88. https://doi.org/10.31599/jsrcs.v1i2.423
Prasetyaningrum, A. U. H. dan P. W. (2021). Penerapan Dataa Minning untuk Prediksi Layanan Produksi Indihome Menggunakan Metode K-NearestNeighbor. JURNAL INFORMATION SYSTEM & ARTIFICIAL INTELLIGENCE, 1(2),100–107.http://repository.uin-suska.ac.id/23008/%0Ahttp://repository.uin-suska.ac.id/23008/2/NURFITRIANTI.pdf
Pratama, F. D., Zufria, I., & Triase, T. (2022). Implementasi Data Minning Menggunakan Algoritmaa NaïveBayes Untuk Klasifikassi Penerima Program Indonesia Pintar. Rabit : Jurnal Teknologi Dan Sistem Informasi Univrab, 7(1), 77–84. https://doi.org/10.36341/rabit.v7i1.2217
Rangkuti, M. Y. R., Alfansyuri, M. V., & Gunawan, W. (2021). PenerapanAlgoritma K-NearestNeighbor (Knn) Dalam MemprediksiDan MenghitungTingkat AkurasiData CuacaDi Indonesia. Hexagon Jurnal Teknik Dan Sains, 2(2), 11–16. https://doi.org/10.36761/hexagon.v2i2.1082
Ryan, I. M., Dhita, P., Ayu, G., & Mastrika, V. (2023). ImplementasiAlgoritma KNNuntukMemprediksi PerformaSiswa Sekolah. Jurnal Nasional Teknologi Informasi Da Aplikasinya, 1(3), 819–826.
Sakti, O., Prakasa, Y., Lhaksamana, K. M., Informatika, F., Telkom, U., Mining, T., Classifier, K. N., & Distance, E. (2018). KlasifikasiTekssDengan Menggunakan Algorittma K-Nearest. 5(3), 8237–8248.
Sekar Seruni, D., Tanzil Furqon, M., & Cahya Wihandika, R. (2020). Siistem Prediksi PertumbuhanJumlah Penduduk Kota Malang MenggunakanMetode K-NearestNeighborRegression. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 4(4), 1075–1082.
Silvilestari, S. (2021). Data Minning Menggunakan AlgoritmaaK-NearestNeighbor Dalam Menentukan KreditMacet BarangElektronik. Jurnal Media Informatika Budidarma, 5(3), 1063. https://doi.org/10.30865/mib.v5i3.3100
Syahra, Y., Santoso, I., & Kustini, R. (2019). Implementassi Data Minning Untuk PrediksiAngka Kelahirran BayiPada Desa SibolangitMenggunakan Multi Regresi. Seminar Nasional Sains & Teknologi Informasi (SENSASI), 1, 687–690.
Syukri Mustafa, M., & Wayan Simpen, I. (2019). Implementassi AlgoritmaaK-Nearest Neighbor (KNN) Untuk Mempredikksi Pasien Terkenna Penyakit Diabettes Pada Puskesmas Manyampa Kabupaten Bulukumba. Februari, 2019(1), 1–10.
DOI: https://doi.org/10.30596/jcositte.v5i1.17991
Refbacks
- There are currently no refbacks.