Sage Journals: Discover world-class research

Abstract

Nonstandard insurers suffer from a peculiar variant of fraud wherein an overwhelming majority of claims have the semblance of fraud. We show that state-of-the-art fraud detection performs poorly when deployed at underwriting. Our proposed framework “FraudBuster” represents a new paradigm in predicting segments of fraud at underwriting in an interpretable and regulation compliant manner. We show that the most actionable and generalizable profile of fraud is represented by market segments with high confidence of fraud and high loss ratio. We show how these segments can be reported in terms of their constituent policy traits, expected loss ratios, support, and confidence of fraud. Overall, our predictive models successfully identify fraud with an area under the precision–recall curve of 0.63 and an f-1 score of 0.769.

Get full access to this article

View all access options for this article.

References

Corum

. 2015. Insurance research council finds that fraud and buildup add up to $7.7 billion in excess payments for auto injury claims. Available online at www.insurancefraud.org/downloads/InsuranceResearchCouncil02-15.pdf (last accessed February 17, 2017).

Derrig

, Johnston

, Sprinkel

. Auto insurance fraud: Measurements and efforts to combat it. Risk Manage Insur Rev. 2006; 9:109–130.

Delegal

, Pittman

. Florida no-fault insurance reform: A step in the right direction. Fla St UL Rev. 2001; 29:103–1.

McChristian

. No fault auto insurance in Florida: Trends, challenges, and costs. Insurance Information Institute, 2011.

Derrig

. Insurance fraud. J Risk Insur. 2002; 69:271–287.

Hoyt

. The effect of insurance fraud on the economic system. J Insur Regul. 1990; 8:30–4.

Schiller

. The impact of insurance fraud detection systems. J Risk Insur. 2006; 73:421–438.

Viaene

, Derrig

, Baesens

, Dedene

. A comparison of state-of-the-art classification techniques for expert automobile insurance claim fraud detection. J Risk Insur. 2002; 69:373–421.

Belhadji

, Dionne

, Tarkhani

. A model for the detection of insurance fraud. Geneva Papers on Risk and Insurance. Issues Pract., 2000; 25:517–538.

10.

Artís

, Ayuso

, Guillén

. Detection of automobile insurance fraud with discrete choice models and misclassified claims. J Risk Insur. 2002; 69:325–340.

11.

Caudill

, Ayuso

, Guillén

. Fraud detection using a multinomial logit model with missing information. J Risk Insur. 2005; 72:539–550.

12.

Lipton

. The mythos of model interpretability. arXiv. 2016; DOI: arXiv:1606.03490.

13.

Zhang

. The optimality of naive bayes. AA. 2004; 1:3.

14.

Quinlan

. C4. 5: Programs for machine learning. Elsevier, 2014.

15.

Zhang

. Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Proceedings of the Twenty-First International Conference on Machine Learning. ACM, 2004, p. 116.

16.

Breiman

. Random forests. Mach Learn. 2001; 45:5–32.

17.

Chen

, Guestrin

. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SigKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016, pp. 785–794.

18.

Fawcett

, Provost

. Adaptive fraud detection. Data Min Knowl Discov. 1997; 1:291–316.

19.

Phua

, Alahakoon

, Lee

. Minority report in fraud detection: Classification of skewed data. ACM SIGKDD Explor Newsl. 2004; 6:50–59.

20.

Bradley

. The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognit. 1997; 30:1145–1159.

21.

Davis

, Goadrich

. The relationship between precision-recall and roc curves. In: Proceedings of the 23rd International Conference on Machine Learning. ACM, 2006, pp. 233–240.

22.

Powers

. Evaluation: From precision, recall and f-measure to roc, informedness, markedness and correlation. J Mach Learn Technol. 2011; 2:37–63.

23.

Brown

, Gottlieb

. Introduction to ratemaking and loss reserving for property and casualty insurance. Actex Publications, 2007.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.26 MB

FraudBuster: Reducing Fraud in an Auto Insurance Market

Abstract

Abstract

Get full access to this article

References

Supplementary Material