Prediksi Laju Pertumbuhan Penduduk Menggunakan Metode Support Vector Regression (Studi Kasus: Kota Malang)

Arynda Kusuma Dewi (Fakultas Ilmu Komputer, Universitas Brawijaya)
Muhammad Tanzil Furqon (Fakultas Ilmu Komputer, Universitas Brawijaya)
Randy Cahya Wihandika (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 4 No 1 (2020): Januari 2020

Population growth rate is a changes population every year in a region. The high population growth rate in Indonesia is something important because it has impact on the economic, social, politic and national defense. Therefore, related parties such as Dinas sosial and BKKBN analyze the factors which related with population growth rate, so it can make some policies to realize balance of population growth. Beside that, population growth prediction is also used by Dispendukcapil to make other budget plans and other needs. In this study, population growth rate is predicted using Support Vector Regression method by comparing the performance of linear kernels with Gaussian kernel RBF used population growth dataset time series in March 2013 until December 2018. The steps to predict population growth rate begin with data normalization, SVR training to get the update lagrange multiplier value and SVR testing to get prediction results and error rates using MAPE. The test results obtained by the MAPE value using a linear kernel 0.0985% and 0.38192% using the Gaussian RBF kernel.