On Bayesian mixture credibility

John W. Lau, Tak Kuen Siu, Hailiang Yang

Research output: Contribution to journalArticle

Abstract

We introduce a class of Bayesian infinite mixture models first introduced by Lo (1984) to determine the credibility premium for a non-homogeneous insurance portfolio. The Bayesian infinite mixture models provide us with much flexibility in the specification of the claim distribution. We employ the sampling scheme based on a weighted Chinese restaurant process introduced in Lo et al. (1996) to estimate a Bayesian infinite mixture model from the claim data. The Bayesian sampling scheme also provides a systematic way to cluster the claim data. This can provide some insights into the risk characteristics of the policyholders. The estimated credibility premium from the Bayesian infinite mixture model can be written as a linear combination of the prior estimate and the sample mean of the claim data. Estimation results for the Bayesian mixture credibility premiums will be presented. © 2006 by Astin Bulletin. All rights reserved.

Original languageEnglish
Pages (from-to)573-588
Number of pages16
JournalASTIN Bulletin: The Journal of the IAA
Volume36
Issue number2
DOIs
Publication statusPublished - Nov 2006

Fingerprint

Credibility
Mixture Model
Sample mean
Insurance
Estimate
Linear Combination
Flexibility
Specification

Keywords

  • Bayesian mixture models
  • Clustering
  • Credibility premium principle
  • Credibility theory
  • Dirichlet process
  • Infinite mixture
  • Risk characteristics
  • Weighted Chinese Restaurant process

Cite this

Lau, John W. ; Siu, Tak Kuen ; Yang, Hailiang. / On Bayesian mixture credibility. In: ASTIN Bulletin: The Journal of the IAA. 2006 ; Vol. 36, No. 2. pp. 573-588.
@article{fe29d4652ef44a3eb201681e6dafed3f,
title = "On Bayesian mixture credibility",
abstract = "We introduce a class of Bayesian infinite mixture models first introduced by Lo (1984) to determine the credibility premium for a non-homogeneous insurance portfolio. The Bayesian infinite mixture models provide us with much flexibility in the specification of the claim distribution. We employ the sampling scheme based on a weighted Chinese restaurant process introduced in Lo et al. (1996) to estimate a Bayesian infinite mixture model from the claim data. The Bayesian sampling scheme also provides a systematic way to cluster the claim data. This can provide some insights into the risk characteristics of the policyholders. The estimated credibility premium from the Bayesian infinite mixture model can be written as a linear combination of the prior estimate and the sample mean of the claim data. Estimation results for the Bayesian mixture credibility premiums will be presented. {\circledC} 2006 by Astin Bulletin. All rights reserved.",
keywords = "Bayesian mixture models, Clustering, Credibility premium principle, Credibility theory, Dirichlet process, Infinite mixture, Risk characteristics, Weighted Chinese Restaurant process",
author = "Lau, {John W.} and Siu, {Tak Kuen} and Hailiang Yang",
year = "2006",
month = "11",
doi = "10.2143/AST.36.2.2017934",
language = "English",
volume = "36",
pages = "573--588",
journal = "ASTIN Bulletin: The Journal of the IAA",
issn = "0515-0361",
publisher = "Peeters Publishers",
number = "2",

}

On Bayesian mixture credibility. / Lau, John W.; Siu, Tak Kuen; Yang, Hailiang.

In: ASTIN Bulletin: The Journal of the IAA, Vol. 36, No. 2, 11.2006, p. 573-588.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On Bayesian mixture credibility

AU - Lau, John W.

AU - Siu, Tak Kuen

AU - Yang, Hailiang

PY - 2006/11

Y1 - 2006/11

N2 - We introduce a class of Bayesian infinite mixture models first introduced by Lo (1984) to determine the credibility premium for a non-homogeneous insurance portfolio. The Bayesian infinite mixture models provide us with much flexibility in the specification of the claim distribution. We employ the sampling scheme based on a weighted Chinese restaurant process introduced in Lo et al. (1996) to estimate a Bayesian infinite mixture model from the claim data. The Bayesian sampling scheme also provides a systematic way to cluster the claim data. This can provide some insights into the risk characteristics of the policyholders. The estimated credibility premium from the Bayesian infinite mixture model can be written as a linear combination of the prior estimate and the sample mean of the claim data. Estimation results for the Bayesian mixture credibility premiums will be presented. © 2006 by Astin Bulletin. All rights reserved.

AB - We introduce a class of Bayesian infinite mixture models first introduced by Lo (1984) to determine the credibility premium for a non-homogeneous insurance portfolio. The Bayesian infinite mixture models provide us with much flexibility in the specification of the claim distribution. We employ the sampling scheme based on a weighted Chinese restaurant process introduced in Lo et al. (1996) to estimate a Bayesian infinite mixture model from the claim data. The Bayesian sampling scheme also provides a systematic way to cluster the claim data. This can provide some insights into the risk characteristics of the policyholders. The estimated credibility premium from the Bayesian infinite mixture model can be written as a linear combination of the prior estimate and the sample mean of the claim data. Estimation results for the Bayesian mixture credibility premiums will be presented. © 2006 by Astin Bulletin. All rights reserved.

KW - Bayesian mixture models

KW - Clustering

KW - Credibility premium principle

KW - Credibility theory

KW - Dirichlet process

KW - Infinite mixture

KW - Risk characteristics

KW - Weighted Chinese Restaurant process

UR - http://www.scopus.com/inward/record.url?scp=35348840445&partnerID=8YFLogxK

U2 - 10.2143/AST.36.2.2017934

DO - 10.2143/AST.36.2.2017934

M3 - Article

VL - 36

SP - 573

EP - 588

JO - ASTIN Bulletin: The Journal of the IAA

JF - ASTIN Bulletin: The Journal of the IAA

SN - 0515-0361

IS - 2

ER -