Journal article
Stochastic loss reserving with mixture density neural networks
Muhammed Taher Al-Mudafer, Benjamin Avanzi, Greg Taylor, Bernard Wong
INSURANCE MATHEMATICS & ECONOMICS | ELSEVIER | Published : 2022
Abstract
In recent years, new techniques based on artificial intelligence and machine learning in particular have been making a revolution in the work of actuaries, including in loss reserving. A particularly promising technique is that of neural networks, which have been shown to offer a versatile, flexible and accurate approach to loss reserving. However, applications of neural networks in loss reserving to date have been primarily focused 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..
View full abstractRelated Projects (2)
Grants
Awarded by Australian Research Council
Funding Acknowledgements
[ "Earlier versions of this paper were presented at the Actuaries Institute 2021 Virtual Summit, and at the ASTIN Online Colloquium. The authors are grateful for constructive comments received from colleagues who attended those events, as well for comments from a referee, that led to improvements of the paper.", "This research was supported under Australian Research Council's Linkage (LP130100723, with funding partners Allianz Australia Insurance Ltd, Insurance Australia Group Ltd, and Suncorp Metway Ltd) and Discovery Projects (DP200101859) funding schemes. The views expressed herein are those of the authors and are not necessarily those of the supporting organisations." ]