Naslov (eng)

APPLICATION OF ARTIFICIAL INTELLIGENCE IN PROJECTING CLAIMS WITHIN NON-LIFE INSURANCE

Autor

Mitrašević, Mirela
Kočović, Jelena
Koprivica, Marija
Graorac, Miona

Publisher

Opis (eng)

Projection of expected claims represents one of the most important traditional roles of actuaries in charge of estimating claims reserves in non-life insurance. Deterministic and stochastic methods are commonly used to determine claims reserves; however, the fact that the projection of claims is based on incomplete data from the past led to the application of machine learning techniques. In this chapter of the monograph, we will first define claims reserves as well as the statistical basis for their calculation. The focus of the methodological part of the chapter will be on the most important claims reserving methods: chain-ladder (CL), including the Mack version of the model, Bornhuetter-Ferguson (BF), Cape Cod (CC), and Generalised Linear Models (GLM). Starting from the hypothesis that applying artificial intelligence can contribute to increased efficiency and innovation in non-life insurance claims reserving, the last section of the chapter will present the results of testing Machine-led Reserving (MLR) algorithms in selecting the most accurate claims prediction method.

Jezik

engleski

Datum

2024

Licenca

Ovo delo je licencirano pod uslovima licence
Creative Commons CC BY-NC-ND 4.0 - Creative Commons Autorstvo - Nekomercijalno - Bez prerada 4.0 International License.

http://creativecommons.org/licenses/by-nc-nd/4.0/legalcode

Predmet

Keywords: artificial intelligence, non-life insurance, claims reserves, machine learning

Deo kolekcije (1)

o:28218

Ekonomski fakultet