Automated Machine Learning in Insurance

TL;DR

This paper presents an AutoML workflow tailored for insurance applications, enabling users without domain expertise to deploy robust ML models efficiently by automating data preprocessing, model selection, and hyperparameter tuning.

Contribution

The paper introduces a specialized AutoML framework for insurance that handles imbalanced data and simplifies ML deployment for non-experts.

Findings

Automated pipeline improves model performance on insurance datasets.

Features like data balancing and ensemble methods address domain-specific challenges.

Open-source code facilitates adoption and reproducibility.

Abstract

Machine Learning (ML) has gained popularity in actuarial research and insurance industrial applications. However, the performance of most ML tasks heavily depends on data preprocessing, model selection, and hyperparameter optimization, which are considered to be intensive in terms of domain knowledge, experience, and manual labor. Automated Machine Learning (AutoML) aims to automatically complete the full life-cycle of ML tasks and provides state-of-the-art ML models without human intervention or supervision. This paper introduces an AutoML workflow that allows users without domain knowledge or prior experience to achieve robust and effortless ML deployment by writing only a few lines of code. This proposed AutoML is specifically tailored for the insurance application, with features like the balancing step in data preprocessing, ensemble pipelines, and customized loss functions. These features are designed to address the unique challenges of the insurance domain, including the imbalanced nature of common insurance datasets. The full code and documentation are available on the GitHub repository. (https://github.com/PanyiDong/InsurAutoML)