Universal structure modeling approach to customer satisfaction index

Abstract

Purpose -Previous researches have proven that customer satisfaction and loyalty are affected by complicated relationships and are challenging to European customer satisfaction index (ECSI) model. Existing approaches mostly limit their hypotheses to linear relationships, which hinder much information that would lead to better modeling and understanding the relationship between customer satisfaction and loyalty. The purpose of this paper is to reveal potential nonlinear and interaction effects that might be embedded in antecedents of ECSI by exemplifying it in Turkish telecommunications sector. Design/methodology/approach -This papar has justified the validity and reliability of the ECSI model implementation in Turk Telekom Company. The path models are tested via conventional structural equation modeling (SEM) and using a novel method, i.e. universal structure modeling with Bayesian neural networks. Findings -The findings of this study reveal that quality has the most important impact on customer satisfaction. The next important construct was found to be the company image. The relationship between customer expectation and customer satisfaction was revealed to be insignificant. This study reveals the fact that while using the ECSI model more attention must be paid to the consideration of potential nonlinear relationships that might be available among model constructs. Originality/value -This research presents uniqueness in that it reveals significant nonlinear relationships between the model constructs of the ECSI model. Previous studies have identified purely linear relationships, which may not hold true in reality. However, in this study it is revealed that improving one determinant of customer satisfaction may not be as worthy as it is assumed to be in theory, which refers to a nonlinear relationship.

Reflections on Partial Least Squares Path Modeling

“…Rather, the true model could differ markedly from the estimated model in terms of the number of composite variables, the pattern of free and fixed parameters, and the causal flow of the model. Therefore, when PLS-PM practitioners do not have a guiding theory, a more rigorous and sophisticated approach is needed to reveal plausible model structures Presently, we are aware of only one technique for model discovery in the PLS-PM context, namely universal structure modeling (USM; Buckler & Hennig-Thurau, 2008;Turkyilmaz, Oztekin, Zaim, & Demirel, 2013), which is implemented in the Neusrel software package (http://www.neusrel.com/welcome/). Briefly, USM proceeds in two steps: (1) the use of PLS-based exploratory algorithms to assign observed variables to a user-specified number of composites; and (2) application of neural networks to discover the optimal system of linear, nonlinear, and interactive pathways among the composites.…”

News-based forecasts of macroeconomic indicators: A semantic path model for interpretable predictions

“…We additionally utilize a Bayesian neural network as the underlying predictive model in order to infer Y from z i , thereby essentially yielding a universal structure model, USM for short (Buckler & Hennig-Thurau, 2008). In fact, universal structure modeling has found to be effective in multiple applications from the fields of decision support and operations research (e. g. Oztekin et al, 2011;Turkyilmaz et al, 2013Turkyilmaz et al, , 2016.…”

Customer demand prediction of service-oriented manufacturing incorporating customer satisfaction

“…A variety of studies find that higher levels of customer satisfaction lead to greater customer loyalty, through increasing loyalty, and it is argued, customer satisfaction helps to secure future revenues (Hu, Kandampully, and Juwaheer 2009;Deng et al 2010;Turkyilmaz et al 2013). Wang (2013) adopted fuzzy Kano model to elicit customer perception of product attributes and extract customer satisfaction to deal with the decision-making problem in product configuration.…”

“…CSI is a structural model based on the assumptions that customer satisfaction is derived from some factors such as perceived value, expectations and image of a firm (Turkyilmaz et al 2013). In this section, SEM is employed to represent the influence factors of CSI and the relationships among them, and it is considered more flexible than other statistical approaches because of its advantages in focusing on the structural level.…”