A Data-Driven Approach to Analyzing Customer Satisfaction Across Insurance Companies using AI Techniques

View at publisher Summarise with VIRAT
Authors: Mangapathi Rao Chintapalli, D Srinivas
Cited by: 0
References: 22

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The current research work focuses on the application of artificial intelligence (AI) in the insurance customer satisfaction analysis. The data-driven strategies can be considered as a useful resource in terms of service satisfaction and retention since the customer satisfaction is one of the significant success indicators in the competitive insurance field. In the research, machine learning algorithms such as decision trees, random forests, and support vectors machines are used in analyzing customer feedback obtained through various sources, including surveys, social media, customer service interactions, among others. The study builds a solid customer satisfaction analysis model, in which the identification of critical satisfaction drivers and the prediction of churned customers were made. It has been demonstrated that AI methods can substantially improve in terms of determining trends and patterns otherwise outside of view when using conventional approaches. The findings emphasize the role of AI in the improvement of customer service strategy and supporting informed decisionmaking in the insurance sector. The paper will add to the existing knowledge base on AI uses in customer experience management and emphasize the possibility of the increased customer satisfaction and operational efficiency of insurance companies when utilizing AI.

Fields of Study & Subjects

Customer churn and segmentation Customer Service Quality and Loyalty AI in Service Interactions

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1102–1109
Publication date
21 January 2026
Language
EN