Classification of climate-related insurance claims using gradient boosting

George Tzougas; Viet Dang; Asif John; Stathis Kroustalis; Debashish Dey; Konstantin Kutzkov

doi:10.26360/2022_6

Classification of climate-related insurance claims using gradient boosting

George Tzougas, Viet Dang, Asif John, Stathis Kroustalis, Debashish Dey, Konstantin Kutzkov

Research output: Contribution to journal › Article › peer-review

173 Downloads (Pure)

Abstract

The aim of this paper is to implement, one of the most representative
supervised learning approaches, the decision tree based ensemble method called gradient boosting for classifying the number of claims caused by storms in Greece using data from a major insurance company operating in Greece. Finally, a machine learning algorithm is used to for categorising the number of claims which have been occurred by a “storm event” into 3 categories: “no claims”, “1 claim”, “2 or more claims”.

Original language	English
Pages (from-to)	149-168
Number of pages	20
Journal	Anales del Instituto de Actuarios Españoles
Issue number	28
DOIs	https://doi.org/10.26360/2022_6
Publication status	Published - 15 Dec 2022

Access to Document

10.26360/2022_6Licence: CC BY-NC-ND

Download pdfFinal published version, 517 KBLicence: CC BY-NC-ND

Cite this

@article{b7e1b589594a416da285e90d79b03739,

title = "Classification of climate-related insurance claims using gradient boosting",

abstract = "The aim of this paper is to implement, one of the most representativesupervised learning approaches, the decision tree based ensemble method called gradient boosting for classifying the number of claims caused by storms in Greece using data from a major insurance company operating in Greece. Finally, a machine learning algorithm is used to for categorising the number of claims which have been occurred by a “storm event” into 3 categories: “no claims”, “1 claim”, “2 or more claims”.",

author = "George Tzougas and Viet Dang and Asif John and Stathis Kroustalis and Debashish Dey and Konstantin Kutzkov",

year = "2022",

month = dec,

day = "15",

doi = "10.26360/2022_6",

language = "English",

pages = "149--168",

journal = "Anales del Instituto de Actuarios Espa{\~n}oles",

issn = "0534-3232",

number = "28",

}

TY - JOUR

T1 - Classification of climate-related insurance claims using gradient boosting

AU - Tzougas, George

AU - Dang, Viet

AU - John, Asif

AU - Kroustalis, Stathis

AU - Dey, Debashish

AU - Kutzkov, Konstantin

PY - 2022/12/15

Y1 - 2022/12/15

N2 - The aim of this paper is to implement, one of the most representativesupervised learning approaches, the decision tree based ensemble method called gradient boosting for classifying the number of claims caused by storms in Greece using data from a major insurance company operating in Greece. Finally, a machine learning algorithm is used to for categorising the number of claims which have been occurred by a “storm event” into 3 categories: “no claims”, “1 claim”, “2 or more claims”.

AB - The aim of this paper is to implement, one of the most representativesupervised learning approaches, the decision tree based ensemble method called gradient boosting for classifying the number of claims caused by storms in Greece using data from a major insurance company operating in Greece. Finally, a machine learning algorithm is used to for categorising the number of claims which have been occurred by a “storm event” into 3 categories: “no claims”, “1 claim”, “2 or more claims”.

U2 - 10.26360/2022_6

DO - 10.26360/2022_6

M3 - Article

SN - 0534-3232

SP - 149

EP - 168

JO - Anales del Instituto de Actuarios Españoles

JF - Anales del Instituto de Actuarios Españoles

IS - 28

ER -

Classification of climate-related insurance claims using gradient boosting

Abstract

Access to Document

Fingerprint

Cite this