COMPARATIVE PERFORMANCE FOR PREDICTIVE MODELLING IN MOTOR INSURANCE CLAIMS
DOI:
https://doi.org/10.11113/jt.v78.10118Keywords:
Predictive modelling, claim frequency, claim severity, regression, BPNN, ANFISAbstract
The expected claim frequency and the expected claim severity are used in predictive modelling motor insurance claims. There are two categories of claims were considered, namely, third party property damage and own damage. Datasets from the year 2001 to 2003 are used to develop the predictive model. This paper proposes three different methods, namely, regression analysis, back propagation neural network and adaptive neuro fuzzy inference system to model claim frequency and claim severity as the two important elements in modelling the motor insurance claims. The experimental results showed that the back propagation neural network model produces more accurate as compared to regression analysis and adaptive neuro fuzzy inference system in predicting the claim frequency and claim severity. For both OD and TPPD claim, the results have shown the lowest MAPE with 0.2191 and 0.6515, and 0.2169 and 0.326, respectively.
References
Azlan, M. Z., Habibollah, H. and Safian, S. 2010. Prediction Of Surface Roughness In The End Milling Machining Using Artificial Neural Network. Expert Systems with Applications. 37(2): 1755-1768.
Bahia, H. S. I. 2013. Using Artificial Neural Network Modelling in Forecasting Revenue: Case Study in National Insurance Company/Iraq. International Journal of Intelligence Science. 3(3):136-143.
Batty, M., Tripathi, A., Kroll, A., Peter Wu, C-S., Moore, D., Stehno, C., Lau, L., Guszcza, J. and Katcher, M. 2010. Predictive Modelling for Life Insurance. Deloitte Consulting LLP.
Behbood, V. and Lu, J. 2011. Intelligent Financial Warning Model Using Fuzzy Neural Network and Case-Based Reasoning. IEEE Symposium on Computational Intelligence for Financial Engineering and Economics. 1-6.
Berry-Stölzle, T. R., Koissi, M. C. and Shapiro, F. A. 2010. Detecting Fuzzy Relationships In Regression Models: The Case Of Insurer Solvency Surveillance In Germany. Insurance: Mathematics and Economics. 46(3): 554-567.
Boyacioglu, M. A. and Avci, D. 2010. An Adaptive Network-Based Fuzzy Inference System (ANFIS) For The Prediction Of Stock Market Return: The Case Of The Istanbul Stock Exchange. Expert Systems with Applications. 37(12): 7908-7912.
Christmann, A. 2004. An Approach To Model Complex High-Dimensional Insurance Data. Allgemeines Statistisches Archiv. 88: 375-397.
Dalkilic, T. E., Tank, F. and Kula, K. S. 2009. Neural Networks Approach For Determining Total Claim Amounts In Insurance. Insurance: Mathematics and Economics. 45(2): 236-241.
David, M. 2015. Auto Insurance Premium Calculation Using Generalized Linear Models. Procedia Economics and Finance. 20: 147-156.
Dugas, C., Chapados, N., Ducharme, R., Saint-Mleux, X. and Vincent, P. 2011. A High-Order Feature Synthesis And Selection Algorithm Applied To Insurance Risk Modelling. International Journal of Business Intelligence and Data Mining. 6(3): 237-258.
Duma, M., B. Twala, and T. Marwala. 2011. Improving The Performance Of The Ripper In Insurance Risk Classification: A Comparitive Study Using Feature Selection. 8th International Conference on Informatics in Control, Automation and Robotics. 203-10.
Frees, E. W., Peng Shi, P. and Valdez, E. A. 2008. Actuarial Applications Of A Hierarchical Insurance Claims Model. ASTIN Bulletin. 39 (1): 165-197.
Frees, E. 2014. Frequency And Severity Models. In E. Edward, G. Meyers, and R. A. Derrig (Eds.). Predictive Modelling Applications in Actuarial Science, Cambridge. Cambridge University Press.
Gorr, W., Olligschlaeger, A. and Thompson, Y. 2003. Short-Term Forecasting Of Crime. International Journal of Forecasting. 19(4): 579-594.
Homayouni, N. and Amiri, A. 2011. Stock Price Prediction Using A Fusion Model Of Wavelet, Fuzzy Logic And ANN. International Conference on E-business, Management and Economics IPEDR, IACSIT Press, Singapore. (25): 277-281.
Huang, Q., Lin, L. and Sun, T. 2011. Some Actuarial Formula of Life Insurance for Fuzzy Markets. Applied Mathematics. 2(8): 1046-1050.
Ibiwoye, A., Ajibola, O. O. E. and Sogunro, A. B. 2012. Artificial Neural Network Model for Predicting Insurance Insolvency. International Journal of Management and Business Research. 2(1): 59-68.
Ismail, N. and Jemain, A. A. 2008. Construction Of An Insurance Scoring System Using Regression Models. Sains Malaysia. 37(4): 412-41.
Kitchen, F. L. 2009. Financial Implications Of Artificial Neural Networks In Automobile Insurance Underwriting. International Journal of Electronic Finance. 3(3): 311-319.
Laas, D., Schmeiser, H. and Wagner, J. 2016. Empirical Findings on Motor Insurance Pricing in Germany, Austria, and Switzerland. Geneva Papers on Risk and Insurance - Issues and Practice. 41(3): 398-431.
Lennon, H. 2011. Generalized Linear Models and their Extensions for Insurance Data. Master of Degree, University of Manchester.
Lin, C. 2009. Using Neural Networks As A Support Tool In The Decision Making For Insurance Industry. Expert Systems with Applications. 36(3): 6914-6917.
Liew, T. and Chen, W. Y. 1998. Intelligence Detection Of Drill Wear. Journal of Mechanical Systems and Signal Processing. 12: 863-873.
Mol, C. D., Giannone, D. and Reichlin, L. 2008. Forecasting Using A Large Number Of Predictors: Is Bayesian Shrinkage A Valid Alternative To Principal Components? Journal of Econometrics. 146(2): 318-328.
Mohamed, M. A., Ismail, H., Razali, A. M., Ismail, N. and Ganiyat, A. U. 2011. Own Damage, Third Party Property Damage Claims And Malaysian Motor Insurance: An Empirical Examination. Australian Journal of Basic and Applied Sciences. 5(7): 1190-1198.
Morata, L. B. 2009. A Priori Ratemaking Using Bivariate Poisson Regression Models. Insurance: Mathematics and Economics. 44(1): 135-141.
Pinquet, J. 2012. Experience Rating In Non-Life Insurance. Working Papers hal-00677100, HAL.
Salcedo-Sanz, S., Cuadra, L., Portilla-Figueras, J. A., Jiménez-Fernández, S. and Alexandre-Cortizo, E. 2012. A Review Of Computational Intelligence Algorithms In Insurance Applications. Statistical And Soft Computing Approaches In Insurance Problems. Nova Science Publishers. 1-50.
Shapiro, F. A. 2007. An Overview Of Insurance Uses Of Fuzzy Logic. Computational Intelligence in Economics and Finance. (II): 25-61.
Shi, P., Feng, X. and Ivantsova, A. 2015. Dependent Frequency–Severity Modelling Of Insurance Claims. Insurance: Mathematics and Economics. 64: 417-428.
Takagi, T. and Sugeno, M. 1983. Derivation Of Fuzzy Control Rules From Human Operator’s Control Action. Proceedings of the IFAC Symposium on Fuzzy Information, Knowledge Representation and Decision Analysis. 55-60.
Wang, F. K.,Chang,K. K.and Tzeng, C. W. 2011. Using Adaptive Network-Based Fuzzy Inference System To Forecast Automobile Sales. Expert Systems with Applications. 38(8): 10587-10593.
Yeo, A. C., Smith, K. A., Willis, R. J., and Brooks, M. 2003. A Comparison Of Soft Computing And Traditional Approaches For Risk Classification And Claim Cost Prediction In The Automobile Insurance Industry. Soft Computing in Measurement and Information Acquisition, Studies in Fuzziness and Soft Computing. Springer-Verlag, 127: 249-261.
Yildiz, B. and Akkoc, S. 2010. Bankruptcy Prediction Using Neuro Fuzzy: An Application in Turkish Bank. International Research Journal of Finance and Economics. 60: 114-126.
Zanganeh, T., Rabiee, M. and Zarei, M. 2011. Applying Adaptive Neuro-Fuzzy Model For Bankruptcy Prediction. International Journal of Computer Application. 20(3): 15-21
Zhang, G., Patuwo, B. E. and Hu, M. Y. 1998. Forecasting With Artificial Neural Networks: The State Of The Art. International Journal of Forecasting. 14(1): 35-62.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
