No abstract

No abstract

Abstract. Underwriting is an important stage in the life insurance process and is concerned with accepting individuals into an insurance fund and on what terms. It is a tedious and labour-intensive process for both the applicant and the underwriting team. An applicant must fill out a large survey containing thousands of questions about their life. The underwriting team must then process this application and assess the risks posed by the applicant and offer them insurance products as a result. Our work implements and evaluates classical data mining techniques to help automate some aspects of the process to ease the burden on the underwriting team as well as optimise the survey to improve the applicant experience. Logistic Regression, XGBoost and Recursive Feature Elimination are proposed as techniques for the prediction of underwriting outcomes. We conduct experiments on a dataset provided by a leading Australian life insurer and show that our early-stage results are promising and serve as a foundation for further work in this space.

The life insurance questionnaire is a large document containing responses in a mixture of structured and unstructured data. The unstructured data poses issues for the user, in the form of extra input effort, and the insurance company, in the form of interpretation and analysis. In this work, we aim to address these problems by proposing a semi-supervised framework for clustering responses into categories using vector space embedding of responses and soft k-means clustering. Our experiments show that our method achieves adequate results. The resulting category clusters from our method can be used for analysis and to replace free text input questions with structured questions in the questionnaire.