Akademik Veri Yönetim Sistemi
EGE 12th INTERNATIONAL CONFERENCE ON APPLIED SCIENCES, İzmir, Türkiye, 26 - 30 Aralık 2024, ss.268, (Özet Bildiri)
Premium is one of the most important issues in the insurance sector. Every person in the world may face different risks. According to these different risks, insurance companies should determine the most appropriate premium for their portfolios. As the portfolio grows, safe and fair pricing becomes more difficult due to the increase in heterogeneity. Some risks may be over-priced while others may be under-priced. In this case, insurance companies need to maintain the balance between different risk groups for premiums, in short, to distinguish between good and bad insureds. In this case, a creditworthiness model, which is one of the experience-based pricing techniques, has been developed to determine the best premium. In this study, since insurance data is generally hierarchical, the two-stage hierarchical creditworthiness model introduced by Jewell is utilized and it is aimed to obtain more accurate and reliable premium estimates as a result of the analysis. The data set used in the research is taken from the Insurance Association of Turkey Motor Vehicles Insurance Statistics Traffic database. As a result of the data obtained, for the hierarchical creditworthiness model, vehicle types are divided according to vehicle types (Commercial Vehicles, Automobiles and Motorcycles) and Z creditworthiness factor is calculated for each of them and premium estimation is made and the results are interpreted.