Evaluation and Selection of Insurance Marketing Schemes Driven by Multisource Big Data

Xian Wu, Huan Liu and Zaoli Yang

Mathematical Problems in Engineering, 2022, vol. 2022, 1-9

Abstract: Insurance marketing is a discipline that maximizes the benefits between policyholders and insurance companies. A big data-driven approach combined with insurance promotions can leverage a wealth of empirical data to develop new customers, motivate existing customers to engage in more activities, and retain existing customers. Insurance business involves a wide variety of scopes and types, and it is labor-intensive and resource-intensive to rely solely on insurance business personnel to process these tedious data. The data-driven approach can find correlations and perform automatic prediction matching according to the characteristics of insurance business data, which saves a lot of time and labor costs. This research uses data mining method and neural network method to mine insurance business data and predict insurance business. This method can accurately capture factors such as the type of insurance business and the amount of the policyholder. The research results show that data mining technology and neural network method have high accuracy and feasibility in predicting insurance business, the prediction error is within 2.38%, and the linear correlation exceeds 0.96. The method used in this study has high accuracy both in terms of new customers and retention of old customers.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/mpe/2022/3642863.pdf (application/pdf)
http://downloads.hindawi.com/journals/mpe/2022/3642863.xml (application/xml)

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:hin:jnlmpe:3642863

DOI: 10.1155/2022/3642863

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().