Sales Forecasting Using Artificial Neural Networks

Marusia Ivanova
Authors registered in the RePEc Author Service: Marusya Ivanova Smokova

Economic Thought journal, 2005, issue 6, 60-81

Abstract: This paper is an attempt to introduce the essence and methodology of Artificial Neural Networks (ANN) in marketing. In order to outline the benefits of their analytical application in marketing management, it is demonstrated how to solve a predictive problem applying one of the most widely used types of ANN - Multi-Layered Feedforward Neural Network. Sales history data about four brands from the Fast Moving Consumer Goods sector in Bulgaria are used for the analysis. Time series are examined for presence of sparsity, outliers and nonstationarity, because these data characteristics can have a significant effect on the accuracy of predictions. It has been proven that ANN gives more accurate predictions in comparison with traditional methods, such as ARIMA and Exponential Smoothing.

JEL-codes: C12 C45 C52 M31 (search for similar items in EconPapers)
Date: 2005
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.ceeol.com/aspx/issuedetails.aspx?issuei ... 41-a89d-7c2f748455b2
Fee access

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bas:econth:y:2005:i:6:p:60-81

Access Statistics for this article

More articles in Economic Thought journal from Bulgarian Academy of Sciences - Economic Research Institute Contact information at EDIRC.
Bibliographic data for series maintained by Diana Dimitrova ().