Forecasting currency circulation data of Bank Indonesia by using hybrid ARIMAX-ANN model

I. Gede Surya Adi Prayoga, Suhartono*, Santi Puteri Rahayu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

The purpose of this study is to forecast currency inflow and outflow data of Bank Indonesia. Currency circulation in Indonesia is highly influenced by the presence of Eid al-Fitr. One way to forecast the data with Eid al-Fitr effect is using autoregressive integrated moving average with exogenous input (ARIMAX) model. However, ARIMAX is a linear model, which cannot handle nonlinear correlation structures of the data. In the field of forecasting, inaccurate predictions can be considered caused by the existence of nonlinear components that are uncaptured by the model. In this paper, we propose a hybrid model of ARIMAX and artificial neural networks (ANN) that can handle both linear and nonlinear correlation. This method was applied for 46 series of currency inflow and 46 series of currency outflow. The results showed that based on out-of-sample root mean squared error (RMSE), the hybrid models are up to10.26 and 10.65 percent better than ARIMAX for inflow and outflow series, respectively. It means that ANN performs well in modeling nonlinear correlation of the data and can increase the accuracy of linear model.

Original languageEnglish
Title of host publication3rd ISM International Statistical Conference 2016, ISM 2016
Subtitle of host publicationBringing Professionalism and Prestige in Statistics
EditorsShaiful Anuar Abu Bakar, Ibrahim Mohamed, Rossita Mohamad Yunus
PublisherAmerican Institute of Physics Inc.
ISBN (Electronic)9780735415126
DOIs
Publication statusPublished - 12 May 2017
Event3rd ISM International Statistical Conference 2016: Bringing Professionalism and Prestige in Statistics, ISM 2016 - Kuala Lumpur, Malaysia
Duration: 9 Aug 201611 Aug 2016

Publication series

NameAIP Conference Proceedings
Volume1842
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

Conference3rd ISM International Statistical Conference 2016: Bringing Professionalism and Prestige in Statistics, ISM 2016
Country/TerritoryMalaysia
CityKuala Lumpur
Period9/08/1611/08/16

Fingerprint

Dive into the research topics of 'Forecasting currency circulation data of Bank Indonesia by using hybrid ARIMAX-ANN model'. Together they form a unique fingerprint.

Cite this