Tree-Based Machine Learning Methods For Vehicle Insurance Claims Size Prediction

TL;DR

This paper explores the application of tree-based ensemble machine learning methods like random forest and gradient boosting to predict vehicle insurance claim sizes, demonstrating their superiority over classical methods.

Contribution

It evaluates and compares various tree-based ML models for claims size prediction, highlighting their effectiveness and importance in insurance big data analysis.

Findings

Tree-based ensemble methods outperform classical least squares in prediction accuracy.

Random forest and gradient boosting provide insights into predictor importance.

Models effectively handle large insurance datasets.

Abstract

Vehicle insurance claims size prediction needs methods to efficiently handle these claims. Machine learning (ML) is one of the methods that solve this problem. Tree-based ensemble learning algorithms are highly effective and widely used ML methods. This study considers how vehicle insurance providers incorporate ML methods in their companies and explores how the models can be applied to insurance big data. We utilize various tree-based ML methods, such as bagging, random forest, and gradient boosting, to determine the relative importance of predictors in predicting claims size and to explore the relationships between claims size and predictors. Furthermore, we evaluate and compare these models' performances. The results show that tree-based ensemble methods are better than the classical least square method. Keywords: claims size prediction; machine learning; tree-based ensemble methods; vehicle insurance.