Automated Machine Learning in Insurance

TL;DR

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 designed to address the unique challenges of the insurance domain.

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)

Figures (9)

• Figure 1: An illustration of AutoML workflow
• Figure 2: Train/Test deviance and runtime on freMTPL2freq dataset
• Figure 3: Train/Test error and runtime on LGPIF dataset
• Figure 4: Train/Test error and runtime on ausprivauto occurrence dataset
• Figure 5: Train/Test deviance and runtime on ausprivauto frequency dataset