File(s) under permanent embargo
Bias-regularised neural-network metamodelling of insurance portfolio risk
conference contribution
posted on 2020-09-28, 00:00 authored by Wei LuoWei Luo, Akib Mashrur, Antonio Robles-KellyAntonio Robles-Kelly, Gang LiGang LiDeep learning models have attracted considerable attention in metamodelling of financial risks for large insurance portfolios. Those models, however, are generally trained in disregard of the collective nature of the data in the portfolio under study. Consequently, the training procedure often suffers from slow convergence, and the trained model often has poor accuracy. This is particularly evident in the presence of extreme individual contracts. In this paper, we advocate the view that the training of a meta-model for a portfolio should be guided by portfolio-level metrics. In particular, we propose an intuitive loss regulariser that explicitly accounts for the portfolio-level bias. Further, this training regulariser can be easily implemented with the minibatch stochastic gradient descent commonly used in training deep neural networks. Empirical evaluations on both simulated data and a benchmark dataset show that the regulariser yields more stable training, resulting in faster convergence and more reliable portfolio-level risk estimates.
History
Event
IJCNN Neural Networks. International Joint Conference (2020 : Glasgow, United Kingdom)Publisher
Institute of Electrical and Electronics Engineers (IEEE)Location
Online : Glasgow, United KingdomPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2020-07-19End date
2020-07-24ISBN-13
978-1-7281-6926-2Publication classification
E1 Full written paper - refereedCopyright notice
2020, IEEETitle of proceedings
IJCNN : Proceedings of the 2020 International Joint Conference on Neural NetworksUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC