AI & ML
On the use of case estimate and transactional payment data in neural networks for individual loss reserving
arXiv stat.ML0 views
arXiv:2601.05274v2 Announce Type: replace-cross Abstract: 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). In environments where covariate data is limited, we find evidence that case estimates will improve predictions substantially, 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.
Source:https://arxiv.org/abs/2601.05274PreviousFunctional Compression as Occam's Razor: Algebraic Complexity from Sensitivity MinimizationNextOn Minimal Observation Time for Recovering Latent Hawkes Networks
Related posts
Orbin' with Amp
0The Changelog

AMD’s Twitter brag that it ‘loves gamers’ met with savage Community Note
0Tom's Hardware

Zane Lowe shares Apple Music Radio audience numbers, recalls ‘crickets’ in the early days
09to5Mac

Google launches Gemini 4 Neon with Carbon quality at Flash speeds, live for AI Pro
09to5Google
One sentence stopped my AI agents inventing data. Bad data that looked normal still fooled them.
0dev.to

How many tokens per second should an LLM serve on one GPU?
0dev.to