Grouping of Contracts in Insurance using Neural Networks

TL;DR

This paper introduces a novel neural network-based framework for grouping insurance contracts, optimizing model points to create smaller, representative portfolios that outperform traditional clustering methods like K-means.

Contribution

The work presents a new neural network approach for contract grouping and model point optimization, eliminating the need for pre-clustering and improving accuracy.

Findings

Outperforms K-means clustering in numerical tests

Can optimize model points for entire portfolios simultaneously

Eliminates pre-clustering step in portfolio grouping

Abstract

Despite the high importance of grouping in practice, there exists little research on the respective topic. The present work presents a complete framework for grouping and a novel method to optimize model points. Model points are used to substitute clusters of contracts in an insurance portfolio and thus yield a smaller, computationally less burdensome portfolio. This grouped portfolio is controlled to have similar characteristics as the original portfolio. We provide numerical results for term life insurance and defined contribution plans, which indicate the superiority of our approach compared to K-means clustering, a common baseline algorithm for grouping. Lastly, we show that the presented concept can optimize a fixed number of model points for the entire portfolio simultaneously. This eliminates the need for any pre-clustering of the portfolio, e.g. by K-means clustering, and therefore presents our method as an entirely new and independent methodology.