Concordance probability in a big data setting: application in non-life insurance

TL;DR

This paper adapts the concordance probability measure for large-scale non-life insurance data, proposing two estimation methods suited for frequency and severity models used in pricing, enhancing model discrimination assessment.

Contribution

It introduces two novel adaptations of the concordance probability estimation tailored for big data in non-life insurance, addressing the challenges of large sample sizes.

Findings

Two estimation procedures suitable for large datasets

Applicable to various versions of concordance probability

Improved discrimination measurement in insurance models

Abstract

The concordance probability or C-index is a popular measure to capture the discriminatory ability of a regression model. In this article, the definition of this measure is adapted to the specific needs of the frequency and severity model, typically used during the technical pricing of a non-life insurance product. Due to the typical large sample size of the frequency data in particular, two different adaptations of the estimation procedure of the concordance probability are presented. Note that the latter procedures can be applied to all different versions of the concordance probability.