Predict health insurance purchase with machine learning techniques
Published in Available at SSRN 3923317, 2021
With the widespread application of product recommender systems, there exists significant scope to enhance predicting customers’ purchasing possibility. In this study, four supervised classification models are constructed based on data from a financial corporation, including logistic regression model, decision tree, bagging, and random forest, to anticipate which customer is more likely to adopt the proposed health insurance policy. After comparing F1 scores using an undersampling train set considering unbalanced sample data, the logistic regression model ultimately represents a superior prediction accuracy for clients’ buying propensity. Therefore, this model has the potential to improve the targeted selling system for this company.
Recommended citation: Liu, Yixuan and Liu, Yixuan and Bo, Keyuan and Yi, Qingxin and Wang, Zhiyi and Sun, Yuwen and Xu, Junjie and Zhang, Xueke and Xu, Ran, Predict Health Insurance Purchase with Machine Learning Techniques (September 14, 2021). Available at SSRN: https://ssrn.com/abstract=3923317 or http://dx.doi.org/10.2139/ssrn.3923317
Download Paper