Providing a Framework for Reforming Premium Rates of Vehicle Collision Coverage with Using Neural Networks Model (A Case Study of Asia Insurance Company)

Document Type : Research Paper


1 Assistant Prof. in Business Administration, Allameh Tabatabaei University, Tehran, Iran

2 Ph.D. Candidate in Business Administration, Islamic Azad University, Babol, Iran

3 Associate Prof. in Industrial Management, Allameh Tabatabaei University, Tehran, Iran

4 Assistant Prof., Faculty of Physical Education and Sports Sciences, University of Guilan, Rasht, Iran


Since vehicle collision coverage, unlike what it seems, is not very profitable for insurance companies and is moving towards making losses, this paper considered the adequacy of measures and rates used by insurance companies, and intended to optimize the methods by employing more scientific approaches. In order to do so, first, the factors affecting the risk of policy holders were identified and after comparing these factors with existing data in the database of surveyed company, the final factors were selected. Then, after preprocessing these data, prediction of the damage class and the quantity of policyholders’ potential damages were accomplished using neural networks model. So that, with using these results and considering their damage ratio, insurance companies could define optimized premium rates for their policies. The results showed that the offered model was able to predict the damage class and potential damages of policy holders respectively with 91 and 87 percent accuracy.


Main Subjects

Anbari, A., Nadali, A. & Eslami Nosrat Abadi, H. (2010). Comparing data mining algorithms for predicting auto insurance policy holders` risk: 4th Iran data mining conference, Tehran: Sharif University of Technology, December 1st, 1-10. (in Persian)
Choobdar, S. (2008). Designing a framework for the future customers of vehicle collision coverage based on data mining) Master`s Thesis), Tarbiat Modarres University, Tehran. (in Persian)
Fathnejad, F. & Izadparast, M. (2011). Presenting a framework for predicting damage level of vehicle collision coverage policy holders with using data mining approach. Insurance World Updates, 156(3), 15-32. (in Persian)
Ghanty, P., Paul, S. & Pal, N. (2009). NEUROSVM: An architecture to reduce the effect of the choice of kernel on the performance of SVM. Journal of Machine Learning Research, 10(3), 591-622.
Gharekhani, M. & Abolghasemi, M. (2011). Data mining applications in insurance industry. Insurance World Updates, 158(5), 5-21. (in Persian)
Guo, L. (2003). Applying DM in property/casualty insurance. University of Central Florida: CAS Committee on Management Data and Information, Florida.
Haji Heydari, N., Khale`, S. & Farahi, A. (2011). Classifying the risk of vehicle collision coverage policy holders with using data mining algorithms. Iranian Journal of Insurance Research, 26(4), 107-129. (in Persian)
Hanafizadeh, P. & Rastkhiz Paydar, N. (2011). A model for risk-based clustering of vehicle collision coverage customers with using data mining technique. Iranian Journal of Insurance Research, 26(2), 55-81. (in Persian)
Iran Insurance Research Center. (2011). Insurance Research Center Annual Statistical Report. Tehran. (in Persian)
Kiavarz Moghaddam, H. & Wang, X. (2014). Vehicle accident severity rules mining using fuzzy granular decision tree. Rough Sets and Current Trends in Computing, 36(85), 280-287.
Mansouri, M. & Kargar, M.J. (2014). Analysis and monitoring of the traffic suburban road accidents using data mining techniques: A case study of Isfahan province in Iran. The Open Transportation Journal, 8(1), 39-49.
Mohammadi, Sh. & Alizadeh, S. (2014). Analyzing the problems of Ayandeh bank`s branches across the country with using data mining technique. Journal of Information Technology Management, 6(2), 333-350. (in Persian)
Momeni, M. (2006). New Approaches in Operations Research (1st ed), University of Tehran: Faculty of Management, Tehran. (in Persian)
Newstead, S. & D`Elia, A. (2007). An investigation into the relationship between vehicle color and crash risk. Monash University Accident Research Center: Report No.263, Melbourne.
Ngai, E., Xiu, L. & Chau, D. (2009). Application of Data Mining techniques in customer relationship management: a Literature Review and Classification. Expert Systems with Application, 36(2), 592-602.
Nisbet, R., Elder, J. & Miner, G. (2009). Handbook of statistical analysis and Data Mining applications, Burlington: Academic Press.
Parnitzke, T. (2008). A Discussion of Risk Assessment Methods for the German Automobile Insurance Industry (Doctoral Dissertation), University of St.Gallen: Institute of Insurance Economics, St. Gallen.
Radfar, R., Nezafati, N. & Yusefi Asl, S. (2014). Clustering customers of e-banking with using data mining algorithms. Journal of Information Technology Management, 6(1), 71-90. (in Persian)
Raut, R. & Nathe, A. (2015). Comparative study of commercial data mining tools. International Journal of Electronics, Communication & Self Computing Science and Engineering, 8, 128-132.
Vosugh, M., Taghavifard, M.T. & Alborzi, M. (2014). Detecting fraud in credit cards with using artificial neural networks. Journal of Information Technology Management, 6(4), 721-746. (in Persian)
Yeo, A., Smith, K., Willis, R. & Brooks, M. (2001). Modeling the effect of premium changes on motor insurance customer retention rates using neural networks. Computational Science. 2074, 390-399.