With the rapid development of China’s insurance industry, insurance fraud incidents are also increasing, especially in the field of auto insurance. Therefore, the vehicle insurance fraud identification model based on extreme learning machine is studied. Because the initial connection weight and hidden layer neuron threshold of the ELM are generated randomly, the recognition results are unstable and the accuracy is affected. Therefore, artificial fish swarm algorithm is used to optimize the model parameters. This paper adaptively improves the step size, visual field and crowding degree of artificial fish swarm. First of all, the principal component analysis method is used to generate the input vector of the ELM model for vehicle insurance fraud. Then the weights and thresholds of the ELM model are optimized by improved artificial fish swarm algorithm. Finally, the model is applied to vehicle insurance fraud identification. The empirical analysis shows that the optimized model has less recognition error and higher recognition stability compared with the traditional ELM classification model.
YanC.WangL.LiuW. et al., Financial early warning of non-life insurance company based on RBF neural network optimized by genetic algorithm, Concurrency & Computation Practice & Experience6 (2017), e4343.
2.
YouB.N., Risk prevention and handling of Insurance fraud-taking vehicle insurance fraud as the path, Shanghai Insurance3 (2018), 13–18.
3.
HassanA.K.I. and AbrahamA., Modeling Insurance Fraud Detection Using Imbalanced Data Classification. Advances in Nature and Biologically Inspired Computing, Springer International Publishing, 2016.
4.
YanC.SunH.T.LiuW. and ChenJ., An integrated method based on hesitant fuzzy theory and RFM model to insurance customers’segmentation and lifetime value determination, Journal of Intelligent & Fuzzy Systems35 (2018), 159–169.
5.
SithicH.L. and BalasubramanianT., Survey of insurance fraud detection using data mining techniques, International Journal of Innovative Technology & Exploring Engineering3 (2013), 62–65.
6.
YanC.SunH.T. and LiuW., Study of fuzzy association rules and cross-selling toward property insurance customers based on FARMA, Journal of Intelligent & Fuzzy Systems31 (2016), 2789–2794.
7.
VermaA.TanejaA. and AroraA., Fraud detection and frequent pattern matching in insurance claims using data mining techniques, Tenth International Conference on Contemporary Computing, IEEE Computer Society, 2017, pp. 1–7.
8.
RawteV. and AnuradhaG., Fraud detection in health insurance using data mining techniques International Conference on Communication, Information & Computing Technology, IEEE, 2015, pp. 1–5.
9.
YaramS., Machine learning algorithms for document clustering and fraud detection, in: International Conference on Data Science & Engineering, IEEE, 2017.
10.
BhowmikR., Detecting auto insurance fraud by data mining techniques, Journal of Emerging Trends in Computing and Information Sciences4 (2011), 371–377.
11.
YeM.H., Research on insurance fraud identification based on BP neural network a case study of China motor vehicle insurance claim, Insurance Research3 (2011), 79–86.
12.
LiY.Q.YanC.LiuW. and LiM.Z., A principle component analysis-based random forest with the potential nearest neighbor method for automobile insurance fraud identification, Applied Soft Computing70 (2018), 1000–1009.
13.
TangJ. and MoY.W., Construction of vehicle insurance anti-fraud system based on data mining technology, Shanghai Insurance11 (2013), 39–42+63.
14.
YanC.LiY.Q. and SunH.T., Research on vehicle insurance fraud identification based on ant colony optimization stochastic forest model, Insurance Research6 (2017), 114–127.
15.
CuiS. and LuanP.P., A review of research on insurance fraud, Director of Economic Research6 (2013), 112–113.
16.
CaudillS.B.AyusoM. and GuillénM., Fraud detection using a multinomial logit model with missing information, Journal of Risk & Insurance72 (2005), 539–550.
17.
ZhangY. and LiM., A new model of water quality evaluation based on particle swarm optimization extreme learning machine, Environmental Science and Technology39 (2016), 135–139.
18.
GeW.H.XuJ.WangY.S.WangM.G.YanP.L. and WuJ., Research on capacity prediction of power capacitor bank based on fish swarm optimization (ELM), Power Capacitor and Reactive Power Compensation39 (2018), 11–15+32.
19.
ZhouH.P. and YuanY., Application of improved fish swarm optimization (ELM) in breast tumor auxiliary diagnosis, Computer Engineering and Science39 (2017), 2145–2152.
20.
LinY.JiH.W.SneeuwN.I.C.O.YeQ., Optimization of image classification method based on fish swarm algorithm for ultimate learning machine, Journal of Agricultural Machinery10 (2017), 156–164.
21.
TianH.L.LiH.G. and XuB.H., Prediction of support vector machine based on improved artificial fish swarm algorithm, Computer Engineering39 (2013), 222–225.
22.
ZhangY.J.LiZ.W. and FengZ.H., An improved artificial fish swarm algorithm based on dynamic parameter adjustment, Journal of Hunan University (Natural Science Edition)39 (2012), 77–82.
23.
LiangY.M. and PeiX.H., Particle swarm optimization artificial fish swarm optimization, Computer Simulation33 (2016), 213–217+281.
24.
LiY.Q.YanC. and SunH.T., Construction and research of vehicle insurance fraud identification model based on ultimate learning machine, Science and Technology and Economy30 (2017), 96–100.
25.
ShaoZ.G., Analysis on early warning index of automobile insurance anti-fraud in insurance company, Modern Economic Information5 (2017), 356.
26.
WeiX.X. and ZhouY.Q., Performance evaluation method for two classes of classification problems based on ROC curves, Computer Technology and Development20 (2010), 47–50.
27.
LuoS.W.OuC.P.ZhangL.P. and ChenH., ROC curve was used to evaluate the diagnostic value of CEA, CYFRA21-1, SCC in non-small cell lung cancer, Chongqing Medicine40 (2011), 250–252+255.
28.
KeN.ZhangH.TayalA. et al., Auto insurance fraud detection using unsupervised spectral ranking for anomaly, Journal of Finance & Data Science2 (2016), 58–75.
