Neural network embedding of the over-dispersed Poisson reserving model
- 3 July 2019
- journal article
- research article
- Published by Taylor & Francis in Scandinavian Actuarial Journal
- Vol. 2020 (1) , 1-29
Abstract
The main idea of this paper is to embed a classical actuarial regression model into a neural network architecture. This nesting allows us to learn model structure beyond the classical actuarial regression model if we use as starting point of the neural network calibration exactly the classical actuarial model. Such models can be fitted efficiently which allows us to explore bootstrap methods for prediction uncertainty. As an explicit example, we consider the cross-classified over-dispersed Poisson model for general insurance claims reserving. We demonstrate how this model can be improved by neural network features.Keywords
This publication has 20 references indexed in Scilit:
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Stochastic Claims Reserving in General InsuranceBritish Actuarial Journal, 2002
- Analytic and bootstrap estimates of prediction errors in claims reservingInsurance: Mathematics and Economics, 1999
- A Stochastic Model Underlying the Chain-Ladder TechniqueBritish Actuarial Journal, 1998
- Distribution-free Calculation of the Standard Error of Chain Ladder Reserve EstimatesASTIN Bulletin, 1993
- A Simple Parametric Model for Rating Automobile Insurance or Estimating IBNR Claims ReservesASTIN Bulletin, 1991
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Learning representations by back-propagating errorsNature, 1986
- Generalized Linear ModelsJournal of the Royal Statistical Society. Series A (General), 1972