Health insurance cross-selling predictions with machine learning for South African consumers

Abstract

Cross-selling is the practice of selling additional products or services to an existing customer to increase business revenue. Cross-selling health insurance is challenging for companies, as they spend significant time meeting with prospective clients without knowing the likelihood of a sale. A health insurance provider often markets additional insurance products to its clients through different channels. This study aims to develop a robust ML model to help health insurance companies identify potential customers likely to engage in cross-selling. Objectives include extracting and preparing customer data from a large South African insurance company using suitable ML techniques. The study also seeks to determine effective algorithms for predicting health insurance cross-selling and to identify influential features for algorithm selection. This study adopted a quantitative research approach focused on extracting health insurance customer data. To achieve this, the study applied ML techniques by using the Python language using a dataset obtained from a large South African insurance company which is a rich repository that contains demographics, health conditions, and policy information. The study applied various ML algorithms, including Random Forest, KNearest Neighbors, XGBoost classifier, and Logistic Regression, feature engineering techniques were employed to enhance predictive accuracy. Analyzing 1,000,000 customer records with 17 features, Random Forest emerged as the top model with an accuracy of 0.91 and an F1 score of 1.00. The study found that customers aged 2570, with prior insurance and longer service history, are more likely to purchase additional health insurance. This study will assist insurance providers in developing a strategy for reaching out to those clients in order to enhance their business operations and revenue.