Neural Networks for the Joint Development of Individual Payments and Claim Incurred
Open Access
Abstract
The goal of this paper is to develop regression models and postulate distributions which can be used in practice to describe the joint development process of individual claim payments and claim incurred. We apply neural networks to estimate our regression models. As regressors we use the whole claim history of incremental payments and claim incurred, as well as any relevant feature information which is available to describe individual claims and their development characteristics. Our models are calibrated and tested on a real data set, and the results are benchmarked with the Chain-Ladder method. Our analysis focuses on the development of the so-called Reported But Not Settled (RBNS) claims. We show benefits of using deep neural network and the whole claim history in our prediction problem.Keywords
Funding Information
- Narodowe Centrum Nauki (2018/31/B/HS4/02150)
This publication has 27 references indexed in Scilit:
- Micro-level stochastic loss reserving for general insuranceScandinavian Actuarial Journal, 2013
- Prediction of outstanding payments in a Poisson cluster modelScandinavian Actuarial Journal, 2011
- Semiparametric model for prediction of individual claim loss reservingInsurance: Mathematics and Economics, 2009
- Individual Claim Loss Reserving Conditioned by Case EstimatesAnnals of Actuarial Science, 2008
- An Individual Claims Reserving ModelASTIN Bulletin, 2007
- Munich chain ladderBlätter der DGVFM, 2004
- Prediction of Outstanding Liabilities in Non-Life InsuranceASTIN Bulletin, 1993
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- The Claims Reserving Problem in Non-Life Insurance: Some Structural IdeasASTIN Bulletin, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989