Authors:
Shengkun Xie
1
;
Anna T. Lawniczak
2
and
Zizhen Wang
2
Affiliations:
1
University of Toronto Mississauga and Ryerson University, Canada
;
2
University of Guelph, Canada
Keyword(s):
Spatially Constrained Clustering, Ratemaking, Geocoding, Gap Statistic, Business Data Analytic, Model Selection.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Clustering
;
Economics, Business and Forecasting Applications
;
Model Selection
;
Pattern Recognition
;
Theory and Methods
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.