Estimation of MTPL claim frequency using GLM, GAM and XGBoost techniques

Käärik, Meelis, juhendajaPuskar, LinnetTartu Ülikool. Loodus- ja täppisteaduste valdkondTartu Ülikool. Matemaatika ja statistika instituut2020-07-012020-07-012020http://hdl.handle.net/10062/68242The purpose of this master’s thesis is to provide an overview of the XGBoost algorithm and examine its suitability to model the claim frequency of motor third party liability insurance. The first three chapters introduce generalized linear models, generalized additive models and the algorithms of gradient boosting and XGBoost. In the fourth chapter, the aforementioned methods are applied on the data of Estonian Motor Insurance Bureau to predict claim frequency.engopenAccessAttribution-NonCommercial-NoDerivatives 4.0 InternationalR (programmeerimiskeel)R (programming language)sõidukikindlustusüldistatud lineaarsed mudelidtehisõpePython (programmeerimiskeel)motor vehicle insurancegeneralized linear modelsmachine learningPython (programming language)Estimation of MTPL claim frequency using GLM, GAM and XGBoost techniquesinfo:eu-repo/semantics/masterThesis