Peramalan Harga Pasar Telur Ayam Ras Di Kota Malang Dengan Menggunakan Metode "SVR - PSO"

Nuriya Fadilah (Fakultas Ilmu Komputer, Universitas Brawijaya)
Arief Andy Soebroto (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 2 No 12 (2018): Desember 2018

Purebred chicken egg become one of the most favorite protein sources in the community because the price is quite affordable than other protein sources that are sold freely in the market. The main problem is the fluctuation of the market price of eggs in Malang, there are times when prices rise and there are times when prices fall. This would be a problem if the price rose from the price in the preceding months. In this research, a system capable to predict the egg market price by using Support Vector Regression (SVR) method to forecast and Particle Swarm Optimization (PSO) method to optimize SVR parameters. The optimization process consists of 4 main stages, namely the normalization stage, SVR training stage, PSO stages, and testing stages. In the SVR performance testing yields the smallest MAPE value of 6.2186%. As for the SVR-PSO performance testing has the smallest MAPE value of 1.8840%.