ARTIFICIAL NEURAL NETWORKS AND STRUCTURAL EQUATION MODELLING: AN EMPIRICAL COMPARISON TO EVALUATE BUSINESS CUSTOMER LOYALTY

Arnaldo Coelho, Luiz Moutinho, Graeme D Hutcheson and Maria Manuela Santos Silva
Additional contact information
Arnaldo Coelho: Faculty of Economics, University of Coimbra, Av. Dias da Silva, 165, 3004–512, Coimbra, Portugal
Luiz Moutinho: Manchester University, UK
Graeme D Hutcheson: Manchester University, UK
Maria Manuela Santos Silva: Faculty of Economics, University of Coimbra, Av. Dias da Silva 165, 3004–5112 Coimbra, Portugal

Chapter 6 in Quantitative Modelling in Marketing and Management, 2012, pp 117-149 from World Scientific Publishing Co. Pte. Ltd.

Abstract: AbstractThis investigation aims to compare the usefulness and the potential contributions of Artificial Neural Networks (ANNs) in the marketing field, particularly, when compared to traditional modelling based on Structural Equations. It uses neural network modelling and structural equation modelling (SEM) to evaluate loyalty in the bank industry in Brazil. Based on a data collection of 229 bank customers (micro, small, and medium companies) from the Northeast of Brazil, the key objective of this study is to investigate the main drivers of customer loyalty in this industry. Neural networks highlight the role of the relationship quality on customer loyalty. The technique SEM confirmed six of the seven hypotheses of the proposed model. The findings highlighted the point that micro, small, and medium companies’ loyalty to their main bank is strongly influenced by affective commitment. Comparing the results achieved from both methodologies, some similarities can be found. Relationship quality is a second order construct that includes satisfaction and affective commitment as its key components, both of which are highlighted on the structural model. The strongest impact in this model is in the relation between satisfaction and affective commitment. This result suggests that, for this marketing problem, ANN and SEM seem to be complementary statistical tools, bringing complementary conclusions.

Keywords: Quantitative Modelling; Statistical; Computer; Marketing; Neural Networks; Fuzzy Logic; k-Clique Model; Meta-heuristics (search for similar items in EconPapers)
Date: 2012
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.worldscientific.com/doi/pdf/10.1142/9789814407724_0006 (application/pdf)
https://www.worldscientific.com/doi/abs/10.1142/9789814407724_0006 (text/html)
Ebook Access is available upon purchase.

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:wsi:wschap:9789814407724_0006

Ordering information: This item can be ordered from

Access Statistics for this chapter

More chapters in World Scientific Book Chapters from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().