Stochastic loss reserving with mixture density neural networks

TL;DR

This paper introduces a Mixture Density Network approach for loss reserving that accurately estimates both the central value and the distribution of outstanding claims, outperforming classical models across various scenarios.

Contribution

It applies MDNs to loss reserving, extends the method with hybrid GLM-MDN and projection constraints, and demonstrates improved accuracy and flexibility over traditional approaches.

Findings

MDN outperforms classical models in estimating claims and quantiles

Hybrid GLM-MDN balances interpretability and accuracy

Methodology is effective with limited data

Abstract

Neural networks offer a versatile, flexible and accurate approach to loss reserving. However, such applications have focused primarily on the (important) problem of fitting accurate central estimates of the outstanding claims. In practice, properties regarding the variability of outstanding claims are equally important (e.g., quantiles for regulatory purposes). In this paper we fill this gap by applying a Mixture Density Network ("MDN") to loss reserving. The approach combines a neural network architecture with a mixture Gaussian distribution to achieve simultaneously an accurate central estimate along with flexible distributional choice. Model fitting is done using a rolling-origin approach. Our approach consistently outperforms the classical over-dispersed model both for central estimates and quantiles of interest, when applied to a wide range of simulated environments of various complexity and specifications. We further extend the MDN approach by proposing two extensions. Firstly, we present a hybrid GLM-MDN approach called "ResMDN". This hybrid approach balances the tractability and ease of understanding of a traditional GLM model on one hand, with the additional accuracy and distributional flexibility provided by the MDN on the other. We show that it can successfully improve the errors of the baseline ccODP, although there is generally a loss of performance when compared to the MDN in the examples we considered. Secondly, we allow for explicit projection constraints, so that actuarial judgement can be directly incorporated in the modelling process. Throughout, we focus on aggregate loss triangles, and show that our methodologies are tractable, and that they out-perform traditional approaches even with relatively limited amounts of data. We use both simulated data -- to validate properties, and real data -- to illustrate and ascertain practicality of the approaches.