Ra. Derrig et Km. Ostaszewski, FUZZY TECHNIQUES OF PATTERN-RECOGNITION IN RISK AND CLAIM CLASSIFICATION, The Journal of risk and insurance, 62(3), 1995, pp. 447-482
Applications of fuzzy set theory to property-liability and life insura
nce have emerged in the last few years through the work of Lemaire (19
90), Cummins and Derrig (1993, 1994), and Ostaszewski (1993). This art
icle continues that line of research by providing an overview of fuzzy
pattern recognition techniques and using them in clustering for risk
and claims classification. The classic clustering problem of grouping
towns into rating territories (DuMouchel, 1983; Conger, 1987) is revis
ited using these fuzzy methods and 1987 through 1990 Massachusetts aut
omobile insurance data. The new problem of classifying claims in terms
of suspected fraud is also addressed using these same fuzzy methods a
nd data drawn from a study of 1989 bodily injury liability claims in M
assachusetts.