Document Type : Research Article
Authors
Insurance Research Center, Tehran, Iran
Abstract
Given the significant increase in fraudulent claims and the resulting financial losses, it is important to adopt a scientific approach to detect and prevent such cases. In fact, not equipping companies with an intelligent system to detect suspicious cases has led to the payment of such losses, which may in the short term lead to customer happiness but eventually will have negative financial consequences for both insurers and insured. Since data labeled fraud is really limited, this paper, provides insurance companies with an algorithm for identifying suspicious cases. This is obtained with the help of an unsupervised algorithm to detect anomalies in the data set. The use of this algorithm enables insurance companies to detect fraudulent patterns that are difficult to detect even for experienced experts. According to the outcomes, the frequency of financial losses, the time of and the type of incident are the most important factors to in detecting suspicious cases.
Keywords
[2] M. Asghari Oskoei, F. Khanizadeh, A. Bahador, Application of Data Mining through Machine Learning Algorithms to Study Effect of Car Features in Predicting Financial Claim of Motor Third Party Liability Insurance, Iranian Journal of Insurance Research, (2020) 35(1) (in Persian).
[3] T. Badriyah, L. Rahmaniah, I. Syarif, Nearest neighbour and statistics method based for detecting fraud in auto insurance, In 2018 International Conference on Applied Engineering (ICAE) , (2018) 1-5.
[4] A. Bodaghi, B. Teimourpour, Automobile insurance fraud detection using social network analysis, In: Moshirpour M., Far B., Alhajj R. (eds) Applications of Data Management and Analysis. Lecture Notes in Social Networks. Springer, Cham. , (2018) 11-16.
[5] M.M. Breunig, H.P. Kriegel, R.T. Ng, J. Sander, LOF: identifying density-based local outliers, In Proceedings of the 2000 ACM SIGMOD international conference on Management of data, (2000) 93-104.
[6] L. Caron, G. Dionne, Insurance fraud estimation: more evidence from the Quebec automobile insurance industry, In Automobile Insurance: Road Safety, New Drivers, Risks, Insurance Fraud and Regulation, (1999) 175-182.
[7] S.B. Caudill, M. Ayuso, M. Guill en, Fraud detection using a multinomial logit model with missing information, Journal of Risk and Insurance, 72(4), (2005) 539-550.
[8] V. Chandola, A. Banerjee, V. Kumar, Anomaly Detection: A Survey, ACM Computing Surveys. vol, 41, (2009) 15.
[9] P. Cunningham, M. Cord, S.J. Delany, Supervised learning. In Machine learning techniques for multimedia , Springer, Berlin, Heidelberg (2008) 21-49.
[10] E.G. Dada, J.S. Bassi, H. Chiroma, A.O. Adetunmbi, O.E. Ajibuwa, Machine learning for email spam ltering: review, approaches and open research problems, Heliyon, 5(6), (2019) e01802.
[11] M.I. Dixon, Recent initiatives in the prevention and detection of insurance fraud, Journal of Financial Crime, (1997).
[12] I. El Naqa, M.J. Murphy, What is machine learning?, In machine learning in radiationoncology (pp. 3-11). Springer, Cham, (2015).
[13] M. Goldstein, S. Uchida, A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data, PloS one, 11(4), (2016) e0152173.
[14] T. Hastie, R. Tibshirani, J. Friedman, Unsupervised learning, In The elements of statistical learning, (2009) 485-585.
[15] G. James, D. Witten, T. Hastie, R. Tibshirani, An introduction to statistical learning (Vol. 112, p. 18), New York: springer, (2013).
[16] F. Khanizadeh, F. Khamesian, A. Bahiraie, Customer Segmentation for Life Insurance in Iran Using K-means Clustering, International Journal of Nonlinear Analysis and Applications, 12(Special Issue), (2021) 633-642.
[17] O.M. Kurland, Combating insurance fraud, Risk Management, 39(7), (1992) 52-54.
[18] K. Nian, Unsupervised Spectral Ranking for Anomaly Detection, (Master's thesis, University of Waterloo), (2014).
[19] K. Nian, H. Zhang, A. Tayal, T. Coleman, Y. Li, Auto insurance fraud detection using unsupervised spectral ranking for anomaly, The Journal of Finance and Data Science, 2(1), (2016) 58-75.
[20] S.M. Palacio, Abnormal pattern prediction: Detecting fraudulent insurance property claims with semi-supervised machine-learning, Data Science Journal, 18(1), (2019).
[21] J. Provost, Nave-bayes vs. rule-learning in classi cation of email, University of Texas at Austin, (1999).
[22] S. Subudhi, S. Panigrahi, Use of optimized Fuzzy C-Means clustering and supervised classi ers for automobile insurance fraud detection, Journal of King Saud University-Computer and Information Sciences, 32(5), (2020) 568-575.
[23] M. Vasu, V. Ravi, A hybrid under-sampling approach for mining unbalanced datasets: applications to banking and insurance, International Journal of Data Mining, Modelling and Management, 3(1), (2011) 75-105.
[24] S. Viaene, R.A. Derrig, B. Baesens, G. Dedene, A comparison of state of the art classi cation techniques for expert automobile insurance claim fraud detection, Journal of Risk and Insurance, 69(3), (2002) 373-421.
[25] S. Viaene, R.A. Derrig, G. Dedene, A case study of applying boosting Naive Bayes to claim fraud diagnosis, IEEE Transactions on Knowledge and Data Engineering, 16(5), (2004) 612-620.
[26] H. Wang, Z. Lei, X. Zhang, B. Zhou, J. Peng, Machine learning basics. Deep learning,(2016) 98-164.
[27] M.A. Wiering, M. Van Otterlo, Reinforcement learning, Adaptation, learning, and optimization, 12(3), (2012) 729.
[28] W. Xu, S. Wang, D. Zhang, B. Yang, Random rough subspace based neural network ensemble for insurance fraud detection, In 2011 Fourth International Joint Conference on Computational Sciences and Optimization, (2011) 1276-1280.
[29] X. Zhu, A.B. Goldberg, Introduction to semi-supervised learning, Synthesis lectures onarti cial intelligence and machine learning, 3(1), (2009) 1-130.
)