Predicting Cross-Selling Health Insurance Products Using Machine-Learning Techniques - Study Abstract

Aug 4, 2026

The study applies machine learning techniques to predict health insurance cross-selling behavior among South African consumers, aiming to help insurers identify prospects with higher likelihoods of purchasing additional health insurance products. Quantitative analysis leverages consumer data in Python with algorithms including random forest, K-nearest neighbors, XGBoost classifier, and logistic regression, supported by feature engineering to improve accuracy. Using 1,000,000 records and 16 features, random forest achieves top performance (accuracy 0.99, F1 1.00). Results show greater propensity among ages 25–70, customers with prior insurance, and longer service history.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages29

Reading Time1 h 13 min

AccessFree to download

Introduction

Cross-selling in health insurance

Role of data analytics and customer datasets

Machine learning for predictive cross-selling

Motivation from the Fourth Industrial Revolution

Search in: Advanced search Journal of Computer Information Systems Latest Articles Submit an article Journal homepage Predicting Cross-Selling Health Insurance Products Using Machine-Learning Techniques Khulekani Mavundla , Surendra Thakur , Emmanuel Adetiba & Abdultaofeek Abayomi Published online: 05 Sep 2024 􀁸 Cite this article 􀁸 [https://doi.org/10.1080/08874417.2024.2395913](https://doi.org/10.1080/08874417.2024.2395913) 􀁸 CrossMark In this article 􀁸 􀁸 View PDF(open in a new window)View EPUB(open in a new window) Formulae display: ? ABSTRACT This study delves into the utilization of Machine Learning (ML) techniques for predicting health insurance cross-selling behavior in South African consumers. The main goal is to create a robust ML model that assists health insurance companies in pinpointing potential customers with higher probabilities of purchasing additional health insurance products. Employing quantitative methodology, the study extracted consumer data and applied various ML algorithms such as random forest, K-nearest neighbors, XGBoost classifier, and logistic regression using Python. Tailored feature engineering techniques were employed to enhance predictive accuracy. Analyzing 1,000,000 customer records with 16 features, Random Forest emerged as the topperforming model, achieving an accuracy score of 0.99 and F1 score of 1.00. The study reveals that customers aged 25–70, with prior insurance and longer service history, are more inclined to purchase additional health insurance products. These findings provide actionable insights for refining marketing strategies, boosting customer acquisition, and increasing revenue. KEYWORDS: 􀁸 Health insurance 􀁸 cross-selling 􀁸 customer churn 􀁸 machine learning algorithms 􀁸 prediction 􀁸 model training Previous articleView latest articlesNext article Introduction The intersection of data analytics and the insurance industry has paved way for innovative approaches to customer relationship management and revenue generation. One particularly intriguing avenue is the exploration of cross-selling opportunities within the health insurance industry.Citation1 Health insurance cross-selling is the practice of insurance companies offering health insurance products to existing consumers (policyholders) in addition to the other products that they are currently being covered, which is a critical component of the broader insurance sector that plays a pivotal role in the business growth and profitability of insurance companies and in safeguarding individuals and families against the financial burdens associated with medical expenses. With the evolving landscape of healthcare and insurance, providers are increasingly recognizing the importance of enhancing customer engagement and expanding their product offerings beyond traditional coverage.Citation2 Healthcare is a basic human right and important to the society and the economy. It consists of all sectors (including insurance), providing services that promote the safety and well-being of the society. The health insurance industry is incredibly significant by ensuring affordable and accessible healthcare for people. It offers financial protection, promotes preventive care, enables risk pooling, and expands access to healthcare services, thus enhancing health outcomes and overall well-being. However, the healthcare sector faces various challenges such as pandemic, health disparity, infectious disease, etc. and it is continuously impacted by technology, thus necessitating data scientists to continuously monitor and respond toward a resilient system. By harnessing the power of data analytics, insurers can gain valuable insights into customer behavior, preferences, and risk profiles.Citation3 The utilization of health insurance customer datasets in this context represents a paradigm shift in how insurance companies approach their business strategies. This research specifically

FAQs

What is the main goal of this study on health insurance cross-selling?

To build a robust machine learning model that helps health insurance companies identify customers with higher probabilities of buying additional health insurance products.

Which machine learning algorithms are used and how is prediction implemented?

The study uses Python and applies random forest, K-nearest neighbors, XGBoost classifier, and logistic regression, supported by feature engineering and quantitative analysis of customer data.

What factors are found to influence customers’ likelihood of purchasing additional coverage?

Customers aged 25–70, those with prior insurance, and those with longer service history show higher inclination to purchase additional health insurance products.

Aug 4, 2026

Upload by Theodore