Time-series Modeling for Consumer Price Index Forecasting using Comparison Analysis of AutoRegressive Integrated Moving Average and Artificial Neural Network

Intan Yuniar Purbasari, Fetty Tri Anggraeny, Nindy Apsari Ardiningrum

2020

Abstract

The Consumer Price Index (CPI) is an index number that measures the average price of goods consumed by households and is one factor that influences inflation in a country. The CPI forecast is calculated in monthly periods each year to anticipate the possibility of a spike in the inflation rate. Forecasting the CPI makes use of past values, commonly known as time-series data (TSD). One method to assist the forecasting process on TSD is the Autoregressive Integrated Moving Average (ARIMA). However, ARIMA is less accurate for nonlinear data problems. Another method that can also be used for forecasting with linear data problems is the Artificial Neural Network (ANN). This study compared the two forecasting methods between ARIMA and ANN by predicting the Indonesian CPI value from January - December 2018. The TSD used is in data on the Indonesian CPI value between January 2009 and December 2017. This study indicates that the ANN method is better than ARIMA because it produces a smaller MSE of 59.23. However, ARIMA is also good because the two methods' forecast results are in the range of the CPI value.

Paper Citation

in Harvard Style

Purbasari I., Anggraeny F. and Ardiningrum N. (2020). Time-series Modeling for Consumer Price Index Forecasting using Comparison Analysis of AutoRegressive Integrated Moving Average and Artificial Neural Network. In Proceedings of the International Conference on Culture Heritage, Education, Sustainable Tourism, and Innovation Technologies - Volume 1: CESIT, ISBN 978-989-758-501-2, pages 599-604. DOI: 10.5220/0010369200003051

in Bibtex Style

@conference{cesit20,
author={Intan Yuniar Purbasari and Fetty Tri Anggraeny and Nindy Apsari Ardiningrum},
title={Time-series Modeling for Consumer Price Index Forecasting using Comparison Analysis of AutoRegressive Integrated Moving Average and Artificial Neural Network},
booktitle={Proceedings of the International Conference on Culture Heritage, Education, Sustainable Tourism, and Innovation Technologies - Volume 1: CESIT,},
year={2020},
pages={599-604},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010369200003051},
isbn={978-989-758-501-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Culture Heritage, Education, Sustainable Tourism, and Innovation Technologies - Volume 1: CESIT,
TI - Time-series Modeling for Consumer Price Index Forecasting using Comparison Analysis of AutoRegressive Integrated Moving Average and Artificial Neural Network
SN - 978-989-758-501-2
AU - Purbasari I.
AU - Anggraeny F.
AU - Ardiningrum N.
PY - 2020
SP - 599
EP - 604
DO - 10.5220/0010369200003051