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 proceedingConference PaperResearchpeer-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 languageEnglish
    Title of host publicationComputational Science – ICCS 2001
    Subtitle of host publicationInternational Conference San Francisco, CA, USA, May 28-30, 2001 Proceedings, Part II
    EditorsVassil N. Alexandrov, Jack J. Dongarra, Benjoe A. Juliano, Rene S. Renner, C. J. Kenneth Tan
    Place of PublicationBerlin Germany
    PublisherSpringer
    Pages390-399
    Number of pages10
    ISBN (Print)3540422331
    DOIs
    Publication statusPublished - 2001
    EventInternational Conference on Computational Science 2001 - San Francisco, United States of America
    Duration: 27 May 200131 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

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume2074
    ISSN (Print)0302-9743

    Conference

    ConferenceInternational Conference on Computational Science 2001
    Abbreviated titleICCS 2001
    Country/TerritoryUnited States of America
    CitySan Francisco
    Period27/05/0131/05/01
    Internet address

    Cite this