https://phaidrabg.bg.ac.rs/o:35578 ISBN: 978-99955-45-45-1 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. University of East Sarajevo Faculty of Business Economics Bijeljina Mitrašević, Mirela Kočović, Jelena Koprivica, Marija Graorac, Miona 2024 info:eu-repo/semantics/conferenceProceedings eng TRANSFORMATION OF THE ECONOMY WITH ARTIFICIAL INTELLIGENCE: PERSPECTIVES, CHALLENGES AND OPPORTUNITIES startpage: 36 endpage: 54 application/pdf 889175 bytes Keywords: artificial intelligence, non-life insurance, claims reserves, machine learning http://creativecommons.org/licenses/by-nc-nd/4.0/legalcode APPLICATION OF ARTIFICIAL INTELLIGENCE IN PROJECTING CLAIMS WITHIN NON-LIFE INSURANCE