AUTHOR=Manathunga Vajira , Zhu Danlei 

TITLE=Unearned premium risk and machine learning techniques

JOURNAL=Frontiers in Applied Mathematics and Statistics

VOLUME=Volume 8 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/applied-mathematics-and-statistics/articles/10.3389/fams.2022.1056529

DOI=10.3389/fams.2022.1056529

ISSN=2297-4687

ABSTRACT=Insurance companies typically divide premiums into earned premiums and unearned premiums. Unearned premium is the portion of premium that is allocated for the remaining period of a policy or premium that still needs to be earned. The unearned premium risk arises when unearned premium is insufficient to cover future losses. There are specific regulatory guidelines to calculate unearned premium reserves; however less attention on any deficiency reserves. Existing research mainly focused on utilizing statistical models to calculate premium deficiency reserves for the unearned premium risk. In this article, we apply machine learning models to calculate reserves for unearned premium risk to an extended warranty data set, which comes under long-duration P \& C insurance contracts. Using two statistical and two machine learning models, we show that machine learning models predict reserves more accurately than the traditional statistical model. Thus, this article encourages actuaries to consider machine learning models in calculating reserves for unearned premium risk.