London Met Repository

Developing strategies to retain organizational insurers using a clustering technique: evidence from the insurance industry

Lists

Tools

Kambiz, Shahroodi, Soroush, Avakh Darestani, Samaneh, Soltani and Adeleh, Eisazadeh Saravani (2024) Developing strategies to retain organizational insurers using a clustering technique: evidence from the insurance industry. Technological Forecasting & Social Change, 201 (123217). pp. 1-14. ISSN 1873-5509

[+][-]

Abstract

Formulating strategies to maintain policyholders is one of the main challenges for most insurance companies in Iran. The purpose of this article is to help marketing strategists of insurance companies predict insurees' churn and develop insurees retention strategies. Since the cost of maintaining an insurance policyholder is approximately one-eighth of the cost of attracting new ones, predicting their churn can help insurance companies adopt proper strategies in advance, which will definitely lead to saving marketing costs and maintaining the insurer's portfolio. Accordingly, the main question of this research is how to classify organizational insurees with the help of the clustering technique. This research is conducted in both qualitative and quantitative phases. In the qualitative phase, by conducting a semi-structured interview (interview protocol) with 15 experts in the insurance industry, the influential factors on policyholders' churn are identified. Then, based on the factors identified in the research literature and comparing them with the interview results, eight main factors are finalized. In the quantitative phase, in order to cluster the organizational insurees, 120 samples from the Iran Insurance Company are selected, and k-means is applied for clustering. Organizational insurees are divided into two groups according to the desired indicators. Using the results of clustering, insurees are divided into four groups, and effective marketing strategies are developed for each group. According to the results, the variable “health care insurance price” has the most effective role in separating the clusters at an error level of <0.01, and on the contrary, the variable “liability insurance amount” has the least important role at an error level of <0.978.

Documents