α-Sutte Indicator: a new method for time series forecasting
Open Access
- 4 June 2018
- journal article
- research article
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1040 (1), 012018
- https://doi.org/10.1088/1742-6596/1040/1/012018
Abstract
α-Sutte Indicator (α-Sutte) was originally from the development of Sutte Indicator. Sutte Indicator can be used to predict the movement of stocks. As the development of science, Sutte Indicator is developed to predict not only the movement of stocks but also able to forecast the data on finance, insurance, and time series data. This method is called α-Sutte Indicator (α-Sutte). α-Sutte was developed by using the principle of the forecasting method of using the previous data. α-Sutte choose because it have best accuracy in forecasting. To implementation and check the accuracy of this method, the Consumer Price Index and Indices by Regions (Turkey) data used in this research. Data taken from January 2003 to June 2017. This data used because CPI data unstable and sometimes difficult to predict using other method. The data is divided into two parts, namely data training and testing. Data training starts from January 2003 to October 2016, and data testing starts from November 2016 to June 2017. To see the accuracy of α-Sutte, benchmark will be conducted from the results of forecasting with other forecasting methods e.g. Multiplicative Holt-Winters, Additive Holt-Winters, and Automatic Time Series Forecasting: The forecast Package for R (AutoARIMA) developed by Hyndman-Khandakar (2008) for the ARIMA/SARIMA model. The comparison of this accuracy is to compare the value of MSE, RMSE, and MAPE of forecasting the result on data training by using the data as reference data. The results are obtained that MSE value of Indicator of α-Sutte is smaller than other methods that is Multiplicative Holt-Winters, Holt-Winters Additive, and ARIMA (1,2,2)(0,0,2)12. Thereby the case for MAPE accuracy value Indicator of α-Sutte better than others method: Multiplicative Holt-Winters, Holt-Winters Additive, and ARIMA (1,2,2)(0,0,2)12.This publication has 8 references indexed in Scilit:
- Forecasting Infant Mortality Rate for China: A Comparison Between α-Sutte Indicator, ARIMA, and Holt-WintersJournal of Physics: Conference Series, 2018
- Artificial Neural Network Optimized Approach for Improving Spatial Cluster Quality of Land Value ZoneInternational Journal of Engineering & Technology, 2018
- A Comparison of α-Sutte Indicator and ARIMA Methods in Renewable Energy Forecasting in IndonesiaInternational Journal of Engineering & Technology, 2018
- Predicting movement of stock of “Y” using Sutte IndicatorCogent Economics & Finance, 2017
- The comparison of Holt–Winters method and Multiple regression method: A case studyEnergy, 2016
- Forecasting US consumer price index: does nonlinearity matter?Applied Economics, 2016
- Modeling and Forecasting Consumer Price Index (Case of Rwanda)American Journal of Theoretical and Applied Statistics, 2016
- Automatic Time Series Forecasting: TheforecastPackage forRJournal of Statistical Software, 2008