A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction

Siu Lau Ho, M. Xie, T. N. Goh

Research output: Journal article publicationJournal articleAcademic researchpeer-review

268 Citations (Scopus)

Abstract

This paper aims to investigate suitable time series models for repairable system failure analysis. A comparative study of the Box-Jenkins autoregressive integrated moving average (ARIMA) models and the artificial neural network models in predicting failures are carried out. The neural network architectures evaluated are the multi-layer feed-forward network and the recurrent network. Simulation results on a set of compressor failures showed that in modeling the stochastic nature of reliability data, both the ARIMA and the recurrent neural network (RNN) models outperform the feed-forward model; in terms of lower predictive errors and higher percentage of correct reversal detection. However, both models perform better with short term forecasting. The effect of varying the damped feedback weights in the recurrent net is also investigated and it was found that RNN at the optimal weighting factor gives satisfactory performances compared to the ARIMA model.
Original languageEnglish
Pages (from-to)371-375
Number of pages5
JournalComputers and Industrial Engineering
Volume42
Issue number2-4
DOIs
Publication statusPublished - 11 Apr 2002
Externally publishedYes

Keywords

  • Box-Jenkins autoregressive integrated moving average model
  • Multi-layer feed-forward neural network
  • Recurrent neural network

ASJC Scopus subject areas

  • Management Science and Operations Research
  • Information Systems and Management
  • Industrial and Manufacturing Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction'. Together they form a unique fingerprint.

Cite this