Journal of the Korean Data and Information Science Society
- Volume 19 Issue 4
- /
- Pages.1419-1427
- /
- 2008
- /
- 1598-9402(pISSN)
Claims Reserving via Kernel Machine
- Kim, Mal-Suk (Department of Applied Statistics, Catholic University of Daegu) ;
- Park, He-Jung (Computer Course Division of General Education and Teacher's Certification, Daegu University) ;
- Hwang, Chang-Ha (Department of Statistics, Dankook University) ;
- Shim, Joo-Yong (Department of Applied Statistics, Catholic University of Daegu)
- Published : 2008.11.30
Abstract
This paper shows the kernel Poisson regression which can be applied in the claims reserving, where the row effect is assumed to be a nonlinear function of the row index. The paper concentrates on the chain-ladder technique, within the framework of the chain-ladder linear model. It is shown that the proposed method can provide better reserve estimates than the Poisson model. The cross validation function is introduced to choose optimal hyper-parameters in the procedure. Experimental results are then presented which indicate the performance of the proposed model.
Keywords
- Anonical parameter;
- Chain-ladder model;
- Cross validation function;
- Generalized linear model;
- Kernel trick;
- Penalized negative log-likelihood;
- Poisson model