Data Size Requirement for Forecasting Daily Crude Oil Price with Neural Networks

ARAS S., Hamdi M.

SCIENTIFIC ANNALS OF ECONOMICS AND BUSINESS, vol.66, no.3, pp.363-388, 2019 (ESCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 66 Issue: 3
  • Publication Date: 2019
  • Doi Number: 10.2478/saeb-2019-0027
  • Journal Name: SCIENTIFIC ANNALS OF ECONOMICS AND BUSINESS
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus
  • Page Numbers: pp.363-388
  • Keywords: neural networks, forecasting, data size, structural break, crude oil price, STRUCTURAL BREAKS, TESTS, MODEL, ALGORITHM, PARAMETER, MARKET
  • Dokuz Eylül University Affiliated: Yes

Abstract

When the literature regarding applications of neural networks is investigated, it appears that a substantial issue is what size the training data should be when modelling a time series through neural networks. The aim of this paper is to determine the size of training data to be used to construct a forecasting model via a multiple-breakpoint test and compare its performance with two general methods, namely, using all available data and using just two years of data. Furthermore, the importance of the selection of the final neural network model is investigated in detail. The results obtained from daily crude oil prices indicate that the data from the last structural change lead to simpler architectures of neural networks and have an advantage in reaching more accurate forecasts in terms of MAE value. In addition, the statistical tests show that there is a statistically significant interaction between data size and stopping rule.