Spatially Constrained Clustering to Define Geographical Rating Territories

Shengkun Xie, Anna T. Lawniczak, Zizhen Wang

Abstract

In this work, spatially constrained clustering of insurance loss cost is studied. The study has demonstrated that spatially constrained clustering is a promising technique for defining geographical rating territories using auto insurance loss data as it is able to satisfy the contiguity constraint while implementing clustering. In the presented work, to ensure statistically sound clustering, advanced statistical approaches, including average silhouette statistic and Gap statistic, were used to determine the number of clusters. The proposed method can also be applied to demographical data analysis and real estate data clustering due to the nature of spatial constraint.

References

  1. A.C. Yeo, K.A. Smith, R. W. and Brooks, M. (2001). Clustering technique for risk classification and prediction of claim costs in the automobile insurance industry. Intelligent Systems in Accounting, Finance and Management, 10:39 - 50.
  2. Grize, Y. (2015). Applications of statistics in the field of general insurance: An overview. International Statistical Review, 83:135-159.
  3. Peck, R. and Kuan, J. (1983). A statistical model of individual accident risk prediction using driver record, territory and other biographical factors. Accident Analysis and Prevention, 15:371-393.
  4. Preparata, F. and Hong, S. (1977). Convex hulls of finite sets of points in two and three dimensions. Commun. ACM, 20:87-93.
  5. R. Tibshirani, G. W. and Hastie, T. (2001). Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63:411-423.
  6. Recchia, A. (2010). Contiguity-constrained hierarchical agglomerative clustering using sas. Journal of Statistical Software, 33:1-8.
  7. Renka, R. (1996). Algorithm 772: Stripack: a constrained two-dimensional delaunay triangulation package. ACM Transactions on Mathematical Software, 22:416-434.
  8. Rousseeuw, P. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Computational and Applied Mathematics, 20:53 - 65.
Download


Paper Citation


in Harvard Style

Xie S., Lawniczak A. and Wang Z. (2017). Spatially Constrained Clustering to Define Geographical Rating Territories . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 82-88. DOI: 10.5220/0006118100820088


in Bibtex Style

@conference{icpram17,
author={Shengkun Xie and Anna T. Lawniczak and Zizhen Wang},
title={Spatially Constrained Clustering to Define Geographical Rating Territories},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={82-88},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006118100820088},
isbn={978-989-758-222-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Spatially Constrained Clustering to Define Geographical Rating Territories
SN - 978-989-758-222-6
AU - Xie S.
AU - Lawniczak A.
AU - Wang Z.
PY - 2017
SP - 82
EP - 88
DO - 10.5220/0006118100820088