<abstract xmlns="http://www.w3.org/1999/xhtml"><p>This paper investigates the impact of risk classification on life insurance ratemaking with particular reference to Bosnia and Herzegovina (BiH). The research is based on a sample of over eighteen thousand insurance policies for passenger vehicles collected over the period 2015-2020. In our empirical investigation we develop a standard risk model based on the application of Poisson Generalized linear models (GLM) for claims frequency estimate and Gamma GLM for claim severity estimate. The analysis reveals that GLM does not provide a reliable parameter estimates for Multi-level factor (MLF) categorical predictors. Although GLM is widely used method to deter insurance premiums, improvements of GLM by using the data mining methods identified in this paper may solve practical challenges for the risk models. The popularity of applying data mining methods in the actuarial community has been growing in recent years due to its efficiency and precision. These models are recommended to be considered in BiH and South East European region in general.</p></abstract>

This paper investigates the impact of risk classification on life insurance ratemaking with particular reference to Bosnia and Herzegovina (BiH). The research is based on a sample of over eighteen thousand insurance policies for passenger vehicles collected over the period 2015-2020. In our empirical investigation we develop a standard risk model based on the application of Poisson Generalized linear models (GLM) for claims frequency estimate and Gamma GLM for claim severity estimate. The analysis reveals that GLM does not provide a reliable parameter estimates for Multi-level factor (MLF) categorical predictors. Although GLM is widely used method to deter insurance premiums, improvements of GLM by using the data mining methods identified in this paper may solve practical challenges for the risk models. The popularity of applying data mining methods in the actuarial community has been growing in recent years due to its efficiency and precision. These models are recommended to be considered in BiH and South East European region in general.

Classification Ratemaking Using Decision Tree in the Insurance Market of Bosnia and Herzegovina

South East European Journal of Economics and Business

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

This paper investigates the impact of risk classification on life insurance ratemaking with particular reference to Bosnia and Herzegovina (BiH). The research...

Classification Ratemaking Using Decision Tree in the Insurance Market of Bosnia and Herzegovina

Pubblicato online: 31 dic 2020

Pagine: 124 - 139

DOI: https://doi.org/10.2478/jeb-2020-0020

Parole chiave
Risk premium, risk classification, generalized linear model, data mining methods, decision trees

© 2020 Amela Omerašević et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Classification Ratemaking Using Decision Tree in the Insurance Market of Bosnia and Herzegovina

Pubblicato online: 31 dic 2020

Pagine: 124 - 139

DOI: https://doi.org/10.2478/jeb-2020-0020

Parole chiaveRisk premium, risk classification, generalized linear model, data mining methods, decision trees

© 2020 Amela Omerašević et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Parole chiave
Risk premium, risk classification, generalized linear model, data mining methods, decision trees