Stochastic loss reserving with mixture density neural networks Article Swipe

MAKE IMPACT

Muhammed Taher Al-Mudafer , Benjamin Avanzi , Greg Taylor , Bernard Wong · YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2108.07924

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.

Type

preprint

Language

en

Landing Page

https://econpapers.repec.org/RePEc:arx:papers:2108.07924

OA Status

green

Related Works

20

OpenAlex ID

https://openalex.org/W3195523336

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3195523336

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2108.07924

Digital Object Identifier

Title

Stochastic loss reserving with mixture density neural networks

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2021

Year of publication

Publication date

2021-08-18

Full publication date if available

Authors

Muhammed Taher Al-Mudafer, Benjamin Avanzi, Greg Taylor, Bernard Wong

List of authors in order

Landing page

https://econpapers.repec.org/RePEc:arx:papers:2108.07924

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://doi.org/10.48550/arxiv.2108.07924

Direct OA link when available

Concepts

Quantile, Computer science, Flexibility (engineering), Range (aeronautics), Artificial neural network, Aggregate (composite), Gaussian, Projection (relational algebra), Mathematical optimization, Econometrics, Artificial intelligence, Algorithm, Mathematics, Statistics, Engineering, Physics, Composite material, Aerospace engineering, Quantum mechanics, Materials science

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

20

Other works algorithmically related by OpenAlex

Full payload