Payments Per Claim Model of Outstanding Claims Reserve Based on Fuzzy Linear Regression
- 6 Downloads
There are uncertainties in factors such as inflation. Historical data and variable values are ambiguous. They lead to ambiguity in the assessment of outstanding claims reserves. The payments per claim model can only perform point estimation. But the fuzzy linear regression is based on fuzzy theory and can directly deal with uncertainty in data. Therefore, this paper proposes a payments per claim model based on fuzzy linear regression. The linear regression method and fuzzy least square method are used to estimate the parameters of the fuzzy regression equation. And the estimated results are introduced into the payments per claim model. Then, the predicted value of each accident reserve is obtained. This result is compared with that of the traditional payments per claim model. And we find that the payments per claim model of estimating the fuzzy linear regression parameters based on the linear programming method is more effective. The model gives the width of the compensation amount for each accident year. In addition, this model solves the problem that the traditional payments per claim model cannot measure the dynamic changes in reserves.
KeywordsOutstanding claims reserve Payments per claim model Fuzzy linear regression Linear programming Least square method
This work was financially supported by the Project of National Natural Science Foundation of China(61502280,61472228).
Compliance with Ethical Standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- 1.Yan, C., Wang, L., Liu, W., Qi, M.: Financial early warning of non-life insurance company based on RBF neural network optimized by genetic algorithm. Concurr. Comput. Pract. Exp. 30(23), 1–11 (2017)Google Scholar
- 6.Ren, Y., Guo, S.Z.: Fuzzy linear regression based on structural element least squares order. Fuzzy Syst. Math. 29(01), 126–133 (2015)Google Scholar
- 7.Guo, Z.X., Han, R., Qi, M.R.: Emergency material demand forecasting model based on multiple fuzzy regression. J. Hebei Univ. (Nat. Sci. Edit.) 37(04), 337–342 (2017)Google Scholar
- 8.Gong, Y.B., Xiang, L., Liu, G.F.: Research on flood disaster classification evaluation method based on fuzzy regression model. Stat. Inf. Forum 2018(5), 65–74 (2018)Google Scholar
- 9.Gong, Y.B., Dai, L.L., Hu, N.: Parameter estimation of fuzzy linear regression model based on COWA operator expectation. Stat. Decis. 2018(2), 15–18 (2018)Google Scholar
- 12.Yan, C., Li, Y.X., Sun, X.H., Liu, Z.B.: Non-life insurance reserve case for indemnity. Insur. Stud. 2015(11), 15–24 (2015)Google Scholar
- 13.Li, Z.X., Meng, S.W.: Automobile insurance pricing model under dependent risk conditions. Insur. Stud. 2016(7), 68–77 (2016)Google Scholar
- 14.Yan, C., Zhang, J., Su, R.: Case-based compensation method based on mathematical programming method considering outliers. Theory Pract. Finance Econ. 38(3), 46–51 (2017)Google Scholar
- 22.Zhou X., Li K.L., Yang Z.B., Xiao G.Q., Li K.Q.: Progressive approaches for Pareto optimal groups computation. IEEE Trans. Knowl. Data Eng. (in press) https://doi.org/10.1109/TKDE.2018.2837117 (2018)
- 25.Chen, Y.D., Li, K.L., Yang, W.D., Xiao, G.Q., Xie, X.H., Li, T.: Performance-aware model for sparse matrix–matrix multiplication on the sunway TaihuLight supercomputer. IEEE Trans. Parallel Distrib. Syst. (in press) https://doi.org/10.1109/TPDS.2018.2871189 (2018)
- 26.Han, T.X.: Non-life Insurance Actuarial, pp. 154–200. Chinese financial & Economic Publishing House, Beijing (2010)Google Scholar