Using Neural Network Analysis to Evaluate Buyer‐Seller Relationships

TLDR

Buyer‑seller relationships are increasingly studied as relational rather than transactional, but quantifying their quality is hampered by complex, interrelated factors and the limitations of traditional regression in handling multicollinearity and missing data, prompting interest in neural network approaches. The study applies neural network analysis to quantify factors influencing buyer‑seller relationship quality. A neural network was built with two output variables—relationship satisfaction and trust—and five input antecedents: salesperson sales orientation, customer orientation, expertise, ethics, and relationship duration. Compared to multiple regression, the neural network produced statistically more significant results, supporting its use and indicating potential for additional marketing applications.

Abstract

Conceptual arguments favouring a relational rather than a transactional approach to the study of buyer‐seller relationships are now well understood. However, attempts to quantify the factors contributing towards relationship quality have been held back by the complexity of the underlying factors and their interrelatedness. Traditional regression techniques are not effective in analysing data with high levels of multi‐collinearity and missing information, typical in many studies of buyer behaviour. Makes use of a relatively new technique – neural network analysis – to try to quantify the factors contributing to buyer‐seller relationship quality. The technique uses a statistically‐based learning procedure modelled on the workings of the human brain which quantifies the relationship between input and output variables through an intermediate “hidden” variable level analogous to the brain. For this study, a neural network was developed with two outcome components of relationship quality (relationship satisfaction and trust), and five input antecedents (the salesperson′s sales orientation, customer orientation, expertise, ethics and the relationship′s duration). In a comparison of multiple regression and neural network techniques, the latter was found to give statistically more significant outcomes. New applications within marketing for neural network analysis are being found. Contributes towards the development of the technique and suggests a number of further possible applications.