Cost-sensitive learning and decision making for Massachusetts PIP claim fraud data

Viaene, StijnDerrig, Richard A.Dedene, Guido (+)2017-12-022017-12-02200410.1002/int.20049http://hdl.handle.net/20.500.12127/4184In this article, we investigate the issue of cost-sensitive classification for a data set of Massachusetts closed personal injury protection (PIP) automobile insurance claims that were previously investigated for suspicion of fraud by domain experts and for which we obtained cost information. After a theoretical exposition on cost-sensitive learning and decision-making methods, we then apply these methods to the claims data at hand to contrast the predictive performance of the documented methods for a selection of decision tree and rule learners. We use standard logistic regression and (smoothed) naive Bayes as benchmarks.enOperations & Supply Chain ManagementCost-sensitive learning and decision making for Massachusetts PIP claim fraud dataInternational journal of Intelligent Systems51528140568763214827