### PERAMALAN DERET WAKTU MENGGUNAKAN MODEL FUNGSI BASIS RADIAL (RBF) DAN AUTO REGRESSIVE INTEGRATED MOVING AVERAGE (ARIMA)

DT Wiyanti(1), R Pulungan(2),

(1) Jurusan Ilmu Komputer dan Elektronika Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Gadjah Mada Yogyakarta
(2) Jurusan Ilmu Komputer dan Elektronika Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Gadjah Mada Yogyakarta

#### Abstract

Â

The accuracy of time series forecasting is the subject of many decision-making processes. Time series use a quantitative approach to employ data from the past to make forecast for the future. Many researches have proposed several methods to solve time series, such as using statistics, neural networks, wavelets, and fuzzy systems. These methods have different advantages and disadvantages. But often the problem in the real world is just too complex that a single method cannot provide adequate solutions, since a single model may not completely identify all the characteristics of time series. In this research, we propose to combine two methods, Auto Regressive Integrated Moving Average (ARIMA) and Radial Basis Function (RBF). This research will make a forecasting for Wholesale Price Index (WPI) and inflation of Indonesian commodity. Each of data is in the range of 2006 to several months in 2012, and each has 6 variables. The results of ARIMA-RBF forecasting method will be compared with ARIMA method and RBF method individually. The result of the analysis shows that the combined method of ARIMA and RBF is more accurate than the ARIMA model or RBF model only. The result can be observed using the visual plot, MAPE, and MSE of all the variables in the two trial data.

#### Keywords

time series; RBF; ARIMA

PDF

#### References

Faruk DO. 2010. A hybrid neural network and ARIMA model for water quality time series prediction. Eng App Intelligence. 23:586-594.

Fauziah L & Suhartono. 2012. Peramalan jumlah kedatangan wisatawan mancanegara ke Indonesia melalui lima pintu kedatangan utama mengggunakan model hibrida ARIMA-ANFIS. Makalah Tugas Akhir. Jurusan Statistika FMIPA-ITS. Surabaya.

Munarsih E. 2011. Penerapan Model ARIMA-Neural Network Hybrid untuk Peramalan Time Series. Thesis. S2 Matematika FMIPA Universitas Gadjah Mada. Yogyakarta.

Sutijo B, Subanar & Guritno S. 2006. Pemilihan hubungan input node pada jaringan syaraf fungsi radial basis. Berkala MIPA 16(1):55-61.

Terui N & Van Dijk HK. 2002. Combined forecast from linear and nonlinear time series model. Int J. of Forecasting 18 (3):421-438.

Zhang G. 2003. Time series forecasting using a hybrid ARIMA and neural network model. J.Neurocomputing 50:159-175.

Zheng F & Zhong S. 2011. Time series forecasting using a hybrid RBF neural network and AR model based on binomial smoothing. World Academy of Science. Eng Technol 75:1471-1475.

### Refbacks

• There are currently no refbacks.