Classification problem in liability insurance using machine learning models: a comparative study

TL;DR

This study compares various machine learning models like nearest neighbor and logistic regression for classifying liability insurance policies into claims and no-claims groups using a specific dataset.

Contribution

It provides a comparative analysis of machine learning techniques applied to liability insurance classification tasks, highlighting their effectiveness.

Findings

Logistic regression and nearest neighbor models perform well in classification.

The study demonstrates the applicability of machine learning in insurance claim prediction.

Model performance varies depending on the feature set used.

Abstract

Underwriting is one of the important stages in an insurance company. The insurance company uses different factors to classify the policyholders. In this study, we apply several machine learning models such as nearest neighbour and logistic regression to the Actuarial Challenge dataset used by Qazvini (2019) to classify liability insurance policies into two groups: 1 - policies with claims and 2 - policies without claims.