Modelling the effect of premium changes on motor insurance customer retention rates using neural networks

Ai Cheo Yeo; Kate A Smith; Robert J Willis; Malcolm Brooks

doi:10.1007/3-540-45718-6_43

Modelling the effect of premium changes on motor insurance customer retention rates using neural networks

Ai Cheo Yeo, Kate A Smith, Robert J Willis, Malcolm Brooks

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

15 Citations (Scopus)

Abstract

This paper describes a neural network modelling approach to premium price sensitivity of insurance policy holders. Clustering is used to classify policy holders into homogeneous risk groups. Within each cluster a neural network is then used to predict retention rates given demographic and policy information, including the premium change from one year to the next. It is shown that the prediction results are significantly improved by further dividing each cluster according to premium change. This work is part of a larger data mining framework proposed to determine optimal premium prices in a data-driven manner.

Original language	English
Title of host publication	Computational Science – ICCS 2001
Subtitle of host publication	International Conference San Francisco, CA, USA, May 28-30, 2001 Proceedings, Part II
Editors	Vassil N. Alexandrov, Jack J. Dongarra, Benjoe A. Juliano, Rene S. Renner, C. J. Kenneth Tan
Place of Publication	Berlin Germany
Publisher	Springer
Pages	390-399
Number of pages	10
ISBN (Print)	3540422331
DOIs	https://doi.org/10.1007/3-540-45718-6_43
Publication status	Published - 2001
Event	International Conference on Computational Science 2001 - San Francisco, United States of America Duration: 27 May 2001 → 31 May 2001 Conference number: 1st https://link-springer-com.ezproxy.lib.monash.edu.au/book/10.1007/3-540-45718-6#toc (Proceedings)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	2074
ISSN (Print)	0302-9743

Conference

Conference	International Conference on Computational Science 2001
Abbreviated title	ICCS 2001
Country/Territory	United States of America
City	San Francisco
Period	27/05/01 → 31/05/01
Internet address	https://link-springer-com.ezproxy.lib.monash.edu.au/book/10.1007/3-540-45718-6#toc (Proceedings)

Access to Document

10.1007/3-540-45718-6_43

Cite this

Yeo, A. C., Smith, K. A., Willis, R. J., & Brooks, M. (2001). Modelling the effect of premium changes on motor insurance customer retention rates using neural networks. In V. N. Alexandrov, J. J. Dongarra, B. A. Juliano, R. S. Renner, & C. J. K. Tan (Eds.), Computational Science – ICCS 2001: International Conference San Francisco, CA, USA, May 28-30, 2001 Proceedings, Part II (pp. 390-399). (Lecture Notes in Computer Science; Vol. 2074). Springer. https://doi.org/10.1007/3-540-45718-6_43

Yeo, Ai Cheo ; Smith, Kate A ; Willis, Robert J et al. / Modelling the effect of premium changes on motor insurance customer retention rates using neural networks. Computational Science – ICCS 2001: International Conference San Francisco, CA, USA, May 28-30, 2001 Proceedings, Part II. editor / Vassil N. Alexandrov ; Jack J. Dongarra ; Benjoe A. Juliano ; Rene S. Renner ; C. J. Kenneth Tan. Berlin Germany : Springer, 2001. pp. 390-399 (Lecture Notes in Computer Science).

@inproceedings{f053cb5b0545437fbe27e26478afb041,

title = "Modelling the effect of premium changes on motor insurance customer retention rates using neural networks",

abstract = "This paper describes a neural network modelling approach to premium price sensitivity of insurance policy holders. Clustering is used to classify policy holders into homogeneous risk groups. Within each cluster a neural network is then used to predict retention rates given demographic and policy information, including the premium change from one year to the next. It is shown that the prediction results are significantly improved by further dividing each cluster according to premium change. This work is part of a larger data mining framework proposed to determine optimal premium prices in a data-driven manner.",

author = "Yeo, {Ai Cheo} and Smith, {Kate A} and Willis, {Robert J} and Malcolm Brooks",

year = "2001",

doi = "10.1007/3-540-45718-6_43",

language = "English",

isbn = "3540422331",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "390--399",

editor = "Alexandrov, {Vassil N.} and Dongarra, {Jack J.} and Juliano, {Benjoe A.} and Renner, {Rene S.} and Tan, {C. J. Kenneth}",

booktitle = "Computational Science – ICCS 2001",

note = "International Conference on Computational Science 2001, ICCS 2001 ; Conference date: 27-05-2001 Through 31-05-2001",

url = "https://link-springer-com.ezproxy.lib.monash.edu.au/book/10.1007/3-540-45718-6#toc",

}

Yeo, AC, Smith, KA, Willis, RJ & Brooks, M 2001, Modelling the effect of premium changes on motor insurance customer retention rates using neural networks. in VN Alexandrov, JJ Dongarra, BA Juliano, RS Renner & CJK Tan (eds), Computational Science – ICCS 2001: International Conference San Francisco, CA, USA, May 28-30, 2001 Proceedings, Part II. Lecture Notes in Computer Science, vol. 2074, Springer, Berlin Germany, pp. 390-399, International Conference on Computational Science 2001, San Francisco, California, United States of America, 27/05/01. https://doi.org/10.1007/3-540-45718-6_43

Modelling the effect of premium changes on motor insurance customer retention rates using neural networks. / Yeo, Ai Cheo; Smith, Kate A; Willis, Robert J et al.

Computational Science – ICCS 2001: International Conference San Francisco, CA, USA, May 28-30, 2001 Proceedings, Part II. ed. / Vassil N. Alexandrov; Jack J. Dongarra; Benjoe A. Juliano; Rene S. Renner; C. J. Kenneth Tan. Berlin Germany : Springer, 2001. p. 390-399 (Lecture Notes in Computer Science; Vol. 2074).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Modelling the effect of premium changes on motor insurance customer retention rates using neural networks

AU - Yeo, Ai Cheo

AU - Smith, Kate A

AU - Willis, Robert J

AU - Brooks, Malcolm

N1 - Conference code: 1st

PY - 2001

Y1 - 2001

N2 - This paper describes a neural network modelling approach to premium price sensitivity of insurance policy holders. Clustering is used to classify policy holders into homogeneous risk groups. Within each cluster a neural network is then used to predict retention rates given demographic and policy information, including the premium change from one year to the next. It is shown that the prediction results are significantly improved by further dividing each cluster according to premium change. This work is part of a larger data mining framework proposed to determine optimal premium prices in a data-driven manner.

AB - This paper describes a neural network modelling approach to premium price sensitivity of insurance policy holders. Clustering is used to classify policy holders into homogeneous risk groups. Within each cluster a neural network is then used to predict retention rates given demographic and policy information, including the premium change from one year to the next. It is shown that the prediction results are significantly improved by further dividing each cluster according to premium change. This work is part of a larger data mining framework proposed to determine optimal premium prices in a data-driven manner.

U2 - 10.1007/3-540-45718-6_43

DO - 10.1007/3-540-45718-6_43

M3 - Conference Paper

SN - 3540422331

T3 - Lecture Notes in Computer Science

SP - 390

EP - 399

BT - Computational Science – ICCS 2001

A2 - Alexandrov, Vassil N.

A2 - Dongarra, Jack J.

A2 - Juliano, Benjoe A.

A2 - Renner, Rene S.

A2 - Tan, C. J. Kenneth

PB - Springer

CY - Berlin Germany

T2 - International Conference on Computational Science 2001

Y2 - 27 May 2001 through 31 May 2001

ER -

Yeo AC, Smith KA, Willis RJ, Brooks M. Modelling the effect of premium changes on motor insurance customer retention rates using neural networks. In Alexandrov VN, Dongarra JJ, Juliano BA, Renner RS, Tan CJK, editors, Computational Science – ICCS 2001: International Conference San Francisco, CA, USA, May 28-30, 2001 Proceedings, Part II. Berlin Germany: Springer. 2001. p. 390-399. (Lecture Notes in Computer Science). https://doi.org/10.1007/3-540-45718-6_43