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

Kambiz Shahroodi · Soroush Avakh Darestani · Adeleh Eisazadeh Saravani

11 citations0/0 files storedTechnological Forecasting and Social Change

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Customer churn and segmentation Customer Service Quality and Loyalty Insurance and Financial Risk Management

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.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 11 citations exist upstream.

References

1990Zero defections: quality comes to services.2018A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees 2009Customer churn prediction by hybrid neural networks 2018Customer churn prediction in telecommunication industry using data certainty 2022Customer Churn Prediction in Telecom Sector Using Machine Learning Techniques 2023Customer churning analysis using machine learning algorithms 2017Early churn prediction with personalized targeting in mobile social games 2023Extreme gradient boosting trees with efficient Bayesian optimization for profit-driven customer churn prediction

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.