Research Article
Forecasting the Inflation using Hybrid SARIMA-Single Exponential Smoothing for Determining Minimum Costs of Living Index in Bandung City
@INPROCEEDINGS{10.4108/eai.18-7-2019.2287710, author={Irfan Dwiguna Sumitra and Rifki Fachrudin and Sri Supatmi}, title={Forecasting the Inflation using Hybrid SARIMA-Single Exponential Smoothing for Determining Minimum Costs of Living Index in Bandung City}, proceedings={Proceedings of the 1st International Conference on Informatics, Engineering, Science and Technology, INCITEST 2019, 18 July 2019, Bandung, Indonesia}, publisher={EAI}, proceedings_a={INCITEST}, year={2019}, month={10}, keywords={inflation forecasting sarima ses khl}, doi={10.4108/eai.18-7-2019.2287710} }- Irfan Dwiguna Sumitra
Rifki Fachrudin
Sri Supatmi
Year: 2019
Forecasting the Inflation using Hybrid SARIMA-Single Exponential Smoothing for Determining Minimum Costs of Living Index in Bandung City
INCITEST
EAI
DOI: 10.4108/eai.18-7-2019.2287710
Abstract
This research aims to produce inflation data forecast and then to forecast the results to an estimation of the Costs of Living Index (KHL). However, this research is limited and merely discuss the KHL by categories of food and beverages entirely. Although inflation could be predicted with high accuracy, surely it could rely upon for making the Government in anticipating future economic activity. Based on previous research, the SARIMA method and Single Exponential Smoothing could show the results of forecasting that is adequate to follow; the value of inflation can be measured by the movements of the actual data. However, this study tried to combine these two methods where the results of the combined method produce more accurate forecasting compared to the results that only used a single method. Based on the results of merging SARIMA with a model (1,0,1) (1,0,1) 12 and Single Exponential Smoothing with an alpha value of 0.6 overall, produces the smallest error value with MAD 114, MSE 0,017 and 0,39% for MAPE. This indicates that the results of the forecasting method of SARIMA method and Single Exponential Smoothing value against inflation are very superfine and accurate. After that, the results of the inflation forecasting needs to be calculated with the value of KHL to become a reference for forecasting the value of KHL for a similar period with inflation forecasting results.