Claims Reserving with a Stochastic Vector Projection

Luis Portugal, Athanasios Pantelous, Hirbod Assa

Research output: Research - peer-reviewArticle

Abstract

In the last three decades, a variety of stochastic reserving models have been proposed in the general insurance literature mainly using (or reproducing) the well-known Chain-Ladder claims-reserving estimates. In practice, when the data do not satisfy the Chain-Ladder assumptions, high prediction errors might occur. Thus, in this article, a combined methodology is proposed based on the stochastic vector projection method and uses the regression through the origin approach of Murphy, but with heteroscedastic errors instead, and different from those that used by Mack. Furthermore, the Mack distribution-free model appears to have higher prediction errors when compared with the proposed one, particularly, for data sets with increasing (regular) trends. Finally, three empirical examples with irregular and regular data sets illustrate the theoretical findings, and the concepts of best estimate and risk margin are reported.

LanguageEnglish
Pages1-18
Number of pages18
JournalNorth American Actuarial Journal
DOIs
StateAccepted/In press - 2018
Externally publishedYes

Cite this

@article{f5a3e3faa9a546ac9dff79309ee30452,
title = "Claims Reserving with a Stochastic Vector Projection",
abstract = "In the last three decades, a variety of stochastic reserving models have been proposed in the general insurance literature mainly using (or reproducing) the well-known Chain-Ladder claims-reserving estimates. In practice, when the data do not satisfy the Chain-Ladder assumptions, high prediction errors might occur. Thus, in this article, a combined methodology is proposed based on the stochastic vector projection method and uses the regression through the origin approach of Murphy, but with heteroscedastic errors instead, and different from those that used by Mack. Furthermore, the Mack distribution-free model appears to have higher prediction errors when compared with the proposed one, particularly, for data sets with increasing (regular) trends. Finally, three empirical examples with irregular and regular data sets illustrate the theoretical findings, and the concepts of best estimate and risk margin are reported.",
author = "Luis Portugal and Athanasios Pantelous and Hirbod Assa",
year = "2018",
doi = "10.1080/10920277.2017.1353429",
pages = "1--18",
journal = "North American Actuarial Journal",
issn = "1092-0277",
publisher = "Taylor & Francis",

}

Claims Reserving with a Stochastic Vector Projection. / Portugal, Luis; Pantelous, Athanasios; Assa, Hirbod.

In: North American Actuarial Journal , 2018, p. 1-18.

Research output: Research - peer-reviewArticle

TY - JOUR

T1 - Claims Reserving with a Stochastic Vector Projection

AU - Portugal,Luis

AU - Pantelous,Athanasios

AU - Assa,Hirbod

PY - 2018

Y1 - 2018

N2 - In the last three decades, a variety of stochastic reserving models have been proposed in the general insurance literature mainly using (or reproducing) the well-known Chain-Ladder claims-reserving estimates. In practice, when the data do not satisfy the Chain-Ladder assumptions, high prediction errors might occur. Thus, in this article, a combined methodology is proposed based on the stochastic vector projection method and uses the regression through the origin approach of Murphy, but with heteroscedastic errors instead, and different from those that used by Mack. Furthermore, the Mack distribution-free model appears to have higher prediction errors when compared with the proposed one, particularly, for data sets with increasing (regular) trends. Finally, three empirical examples with irregular and regular data sets illustrate the theoretical findings, and the concepts of best estimate and risk margin are reported.

AB - In the last three decades, a variety of stochastic reserving models have been proposed in the general insurance literature mainly using (or reproducing) the well-known Chain-Ladder claims-reserving estimates. In practice, when the data do not satisfy the Chain-Ladder assumptions, high prediction errors might occur. Thus, in this article, a combined methodology is proposed based on the stochastic vector projection method and uses the regression through the origin approach of Murphy, but with heteroscedastic errors instead, and different from those that used by Mack. Furthermore, the Mack distribution-free model appears to have higher prediction errors when compared with the proposed one, particularly, for data sets with increasing (regular) trends. Finally, three empirical examples with irregular and regular data sets illustrate the theoretical findings, and the concepts of best estimate and risk margin are reported.

UR - http://www.scopus.com/inward/record.url?scp=85033676782&partnerID=8YFLogxK

U2 - 10.1080/10920277.2017.1353429

DO - 10.1080/10920277.2017.1353429

M3 - Article

SP - 1

EP - 18

JO - North American Actuarial Journal

T2 - North American Actuarial Journal

JF - North American Actuarial Journal

SN - 1092-0277

ER -