Modelling and evaluating customer loyalty using neural networks: Evidence from startup insurance companies

Artikel

The purpose of this study is to investigate the customer-service provider relationship in the insurance industry using artificial neural networks and linear regression. Using a sample of 389 customers from 10 different startup insurance companies, it was found that artificial neural networks are an efficient way to evaluate the factors affecting customer loyalty. The results indicated that customer satisfaction and perceived value are significant predictors of customer loyalty. Additionally, it was found that trust, perceived quality, and empathy have a significant impact on both customer satisfaction and perceived value. The results also showed that customer commitment to service provider is positively associated with customer satisfaction and loyalty. After comparing the performance of linear regression models with artificial neural networks, it was found that the use of neural networks is a better approach for analyzing the customer loyalty, satisfaction, and perceived value. The use of new techniques such as artificial neural networks for analyzing the customer behavior can be particularly beneficial for startup companies who aspire to gain competitive advantage over their strong and well-established rivals.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Journal: Future Business Journal ; ISSN: 2314-7210 ; Volume: 2 ; Year: 2016 ; Issue: 1 ; Pages: 15-30 ; Amsterdam: Elsevier

Classification and Topics

• Classification: Management
• Subject: Artificial neural networks ; Customer loyalty ; Insurance companies ; Relationship marketing ; Startups

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Ansari, Azarnoush ; Riasi, Arash
• Event: Veröffentlichung
• (who): Elsevier
• (where): Amsterdam
• (when): 2016

Further information

• DOI: doi:10.1016/j.fbj.2016.04.001
• Handle: http://hdl.handle.net/10419/187938
• Last update: 10.03.2025, 11:43 AM CET