Saved in:
Bibliographic Details
Main Authors: Avanzi, Benjamin, Lambrianidis, Matthew, Taylor, Greg, Wong, Bernard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2601.05274
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911362187264000
author Avanzi, Benjamin
Lambrianidis, Matthew
Taylor, Greg
Wong, Bernard
author_facet Avanzi, Benjamin
Lambrianidis, Matthew
Taylor, Greg
Wong, Bernard
contents The use of neural networks trained on individual claims data has become increasingly popular in the actuarial reserving literature. We consider how to best input historical payment data in neural network models. Additionally, case estimates are also available in the format of a time series, and we extend our analysis to assessing their predictive power. In this paper, we compare a feed-forward neural network trained on summarised transactions to a recurrent neural network equipped to analyse a claim's entire payment history and/or case estimate development history. We draw conclusions from training and comparing the performance of the models on multiple, comparable highly complex datasets simulated from SPLICE (Avanzi, Taylor and Wang, 2023). We find evidence that case estimates will improve predictions significantly, but that equipping the neural network with memory only leads to meagre improvements. Although the case estimation process and quality will vary significantly between insurers, we provide a standardised methodology for assessing their value.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05274
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the use of case estimate and transactional payment data in neural networks for individual loss reserving
Avanzi, Benjamin
Lambrianidis, Matthew
Taylor, Greg
Wong, Bernard
Statistical Finance
Machine Learning
91G70, 91G60, 62P05, 91B30
The use of neural networks trained on individual claims data has become increasingly popular in the actuarial reserving literature. We consider how to best input historical payment data in neural network models. Additionally, case estimates are also available in the format of a time series, and we extend our analysis to assessing their predictive power. In this paper, we compare a feed-forward neural network trained on summarised transactions to a recurrent neural network equipped to analyse a claim's entire payment history and/or case estimate development history. We draw conclusions from training and comparing the performance of the models on multiple, comparable highly complex datasets simulated from SPLICE (Avanzi, Taylor and Wang, 2023). We find evidence that case estimates will improve predictions significantly, but that equipping the neural network with memory only leads to meagre improvements. Although the case estimation process and quality will vary significantly between insurers, we provide a standardised methodology for assessing their value.
title On the use of case estimate and transactional payment data in neural networks for individual loss reserving
topic Statistical Finance
Machine Learning
91G70, 91G60, 62P05, 91B30
url https://arxiv.org/abs/2601.05274