Abstract
Insurance forecasting is a matter of vital importance to insurance companies for analyzing of annual income, premium and loss reserving, loss payment, etc. Recent years have also seen increasing discussion within the actuarial community of the need for insurance forecasting techniques that are more solidly grounded in rigorous machine learning methodologies. Taking advantages of knowledge-reuse and learning capability for dealing with uncertainties, hybridization of neural networks and fuzzy logic could enhance the accuracy of forecasting for insurance applications. In this paper, we propose a novel neuro-fuzzy inference system for insurance forecasting. It uses multiple parameter sets where each set is responsible for a small subset of records. The aim of each parameter set is to minimize Mean Square Error within records of the subset. The learning strategy and a rule reduction method are also proposed. Empirically validation on the benchmark and real insurance datasets show the advantages of the new system.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Shapiro, A.F.: An overview of insurance uses of fuzzy logic. In: Chen, S.-H., Wang, P.P., Kuo, T.W. (eds.) Computational Intelligence in Economics and Finance, pp. 25–61. Springer, Heidelberg (2007)
Shapiro, F.: Fuzzy logic in insurance. Insur. Math. Econ. 35(2), 399–424 (2004)
Shapiro, F.: Insurance applications of neural networks, fuzzy logic, and genetic algorithms. In: Intelligent and Other Computational Techniques in Insurance: Theory and Applications (2003)
Ana-Maria, B., Ghiorghe, B.: Application of autoregressive models for forecasting marine insurance market. Ovidius Univ. Ann. Ser. Econ. Sci. 13(1), 1125–1129 (2013)
De Alba, E., Nieto-Barajas, L.E.: Claims reserving: a correlated Bayesian model. Ins. Math. Econ. 43, 368–376 (2008)
De Alba, E.: Bayesian estimation of outstanding claims reserves. N. Am. Act. J. 6(4), 1–20 (2002)
De Alba, E.: Claims reserving when there are negative values in the runoff triangle: Bayesian analysis using the three-parameter log-normal distribution. N. Am. Act. J. 10(3), 1–15 (2006)
Gaver, J.J., Paterson, J.S.: Do insurers manipulate loss reserves to mask insolvency problems? J. Acc. Econ. 37, 393–416 (2004)
Antonio, K., Beirlant, J.: Issues in claims reserving and credibility: a semiparametric approach with mixed models. J. Risk Ins. 75, 643–676 (2008)
Bernoth, K., Pick, A.: Forecasting the fragility of the banking and insurance sectors. J. Bank. Finance 35(4), 807–818 (2011)
Abdullah, L., Rahman, M.N.A.: Employee likelihood of purchasing health insurance using fuzzy inference system. Int. J. Comput. Sci. 9(1), 112–116 (2012)
Son, L.H., Linh, N.D., Long, H.V.: A lossless DEM compression for fast retrieval method using fuzzy clustering and MANFIS neural network. Eng. Appl. Artif. Intell. 29, 33–42 (2014)
Martínez-Miranda, M.D., Nielsen, J.P., Wüthrich, M.V.: Statistical modelling and forecasting of outstanding liabilities in non-life insurance. SORT 36(2), 195–218 (2012)
Wüthrich, M.V., Merz, M.: Stochastic Claims Reserving Methods in Insurance. John Wiley & Sons, West Sussex (2008)
Siddique, N., Adeli, H.: Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing. John Wiley & Sons (2013)
England, P.D., Verrall, R.J.: Stochastic claims reserving in general insurance. Br. Act. J. 8, 443–518 (2002)
Mulquiney, P., et al.: Artificial Neural Networks in Insurance Loss Reserving (2011)
Mack, T.: Measuring the Variability of Chain Ladder Reserve Estimates, Casualty Actuarial Society Forum, pp. 101–182 (1994)
Kaymak, U.: Defining a financial forecasting model for healthcare insurance companies, Eindhoven University of Technology (2013)
UCI Machine Learning Repository, Insurance Company Benchmark (COIL 2000) Data Set (2015). https://archive.ics.uci.edu/ml/datasets/Insurance+Company+Benchmark+(COIL+2000)
Beaver, W.H., McNichols, M.F., Nelson, K.K.: Management of the loss reserve accrual and the distribution of earnings in the property-casualty insurance industry. J. Acc. Econ. 35, 347–376 (2003)
Zhang, Y., Dukic, V., Guszcza, J.: A Bayesian non-linear model for forecasting insurance loss payments. J. R. Stat. Soc. Ser. A (Stat. Soc.) 175(2), 637–656 (2012)
Acknowledgement
The authors would like to thank the Center for High Performance Computing, VNU University of Science for executing the program on IBM Cluster 1350 server.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Son, L.H., Khuong, M.N., Tuan, T.M. (2017). A New Neuro-Fuzzy Inference System for Insurance Forecasting. In: Akagi, M., Nguyen, TT., Vu, DT., Phung, TN., Huynh, VN. (eds) Advances in Information and Communication Technology. ICTA 2016. Advances in Intelligent Systems and Computing, vol 538. Springer, Cham. https://doi.org/10.1007/978-3-319-49073-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-49073-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49072-4
Online ISBN: 978-3-319-49073-1
eBook Packages: EngineeringEngineering (R0)