Improving Insurance Catastrophic Data with Resampling and GAN Methods

TL;DR

This paper introduces resampling and GAN-based methods to enhance catastrophic insurance data quality, validated through experiments on real and simulated data, with a focus on error metrics and expert opinion integration.

Contribution

It proposes novel resampling and GAN techniques specifically tailored for improving catastrophic insurance datasets, including a fuzzy expert opinion algorithm.

Findings

GAN and resampling methods improve data quality based on MSE and MAE.

Simulated and real data experiments demonstrate effectiveness.

Fuzzy expert opinion algorithm aids in data assessment.

Abstract

The precise and large dataset concerning catastrophic events is very important for insurers. To improve the quality of such data three methods based on the bootstrap, bootknife, and GAN algorithms are proposed. Using numerical experiments and real-life data, simulated outputs for these approaches are compared based on the mean squared (MSE) and mean absolute errors (MAE). Then, a direct algorithm to construct a fuzzy expert's opinion concerning such outputs is also considered.