Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving Data
In automobile insurance, it is common to adopt a Poisson regression model to predict the number of claims as part of the actuarial pricing process. The Poisson assumption can rarely be justified, often due to overdispersion, and alternative modeling is often considered, typically zero-inflated model...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Risks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9091/10/4/83 |
| _version_ | 1797409386977558528 |
|---|---|
| author | Jennifer S. K. Chan S. T. Boris Choy Udi Makov Ariel Shamir Vered Shapovalov |
| author_facet | Jennifer S. K. Chan S. T. Boris Choy Udi Makov Ariel Shamir Vered Shapovalov |
| author_sort | Jennifer S. K. Chan |
| collection | DOAJ |
| description | In automobile insurance, it is common to adopt a Poisson regression model to predict the number of claims as part of the actuarial pricing process. The Poisson assumption can rarely be justified, often due to overdispersion, and alternative modeling is often considered, typically zero-inflated models, which are special cases of finite mixture distributions. Finite mixture regression modeling of telematics data is challenging to implement since the huge number of covariates computationally prohibits the essential variable selection needed to attain a model with desirable predictive power devoid of overfitting. This paper aims at devising an algorithm that can carry the task of variable selection in the presence of a large number of covariates. This is achieved by generating sub-samples of the data corresponding to each component of the Poisson mixture, and wherein variable selection is applied following the enhancement of the Poisson assumption by means of controlling the number of zero claims. The resulting algorithm is assessed by measuring the out-of-sample AUC (Area Under the Curve), a Machine Learning tool for quantifying predictive power. Finally, the application of the algorithm is demonstrated by using data of claim history and telematics data describing driving behavior. It transpires that unlike alternative algorithms related to Poisson regression, the proposed algorithm is both implementable and enjoys an improved AUC (0.71). The proposed algorithm allows more accurate pricing in an era where telematics data is used for automobile insurance. |
| first_indexed | 2024-03-09T04:14:54Z |
| format | Article |
| id | doaj.art-3a64456869ea473a8684308953e01b57 |
| institution | Directory Open Access Journal |
| issn | 2227-9091 |
| language | English |
| last_indexed | 2024-03-09T04:14:54Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Risks |
| spelling | doaj.art-3a64456869ea473a8684308953e01b572023-12-03T13:55:55ZengMDPI AGRisks2227-90912022-04-011048310.3390/risks10040083Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving DataJennifer S. K. Chan0S. T. Boris Choy1Udi Makov2Ariel Shamir3Vered Shapovalov4School of Mathematics and Statistics, The University of Sydney, Sydney, NSW 2006, AustraliaDiscipline of Business Analytics, The University of Sydney, Sydney, NSW 2006, AustraliaActuarial Resreach Center, University of Haifa, Haifa 3498838, IsraelEfi Arazi School of Computer Science, Reichman University, Herzliya 4610101, IsraelActuarial Resreach Center, University of Haifa, Haifa 3498838, IsraelIn automobile insurance, it is common to adopt a Poisson regression model to predict the number of claims as part of the actuarial pricing process. The Poisson assumption can rarely be justified, often due to overdispersion, and alternative modeling is often considered, typically zero-inflated models, which are special cases of finite mixture distributions. Finite mixture regression modeling of telematics data is challenging to implement since the huge number of covariates computationally prohibits the essential variable selection needed to attain a model with desirable predictive power devoid of overfitting. This paper aims at devising an algorithm that can carry the task of variable selection in the presence of a large number of covariates. This is achieved by generating sub-samples of the data corresponding to each component of the Poisson mixture, and wherein variable selection is applied following the enhancement of the Poisson assumption by means of controlling the number of zero claims. The resulting algorithm is assessed by measuring the out-of-sample AUC (Area Under the Curve), a Machine Learning tool for quantifying predictive power. Finally, the application of the algorithm is demonstrated by using data of claim history and telematics data describing driving behavior. It transpires that unlike alternative algorithms related to Poisson regression, the proposed algorithm is both implementable and enjoys an improved AUC (0.71). The proposed algorithm allows more accurate pricing in an era where telematics data is used for automobile insurance.https://www.mdpi.com/2227-9091/10/4/83mixture poisson regressionvariable selectiontelematics |
| spellingShingle | Jennifer S. K. Chan S. T. Boris Choy Udi Makov Ariel Shamir Vered Shapovalov Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving Data Risks mixture poisson regression variable selection telematics |
| title | Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving Data |
| title_full | Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving Data |
| title_fullStr | Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving Data |
| title_full_unstemmed | Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving Data |
| title_short | Variable Selection Algorithm for a Mixture of Poisson Regression for Handling Overdispersion in Claims Frequency Modeling Using Telematics Car Driving Data |
| title_sort | variable selection algorithm for a mixture of poisson regression for handling overdispersion in claims frequency modeling using telematics car driving data |
| topic | mixture poisson regression variable selection telematics |
| url | https://www.mdpi.com/2227-9091/10/4/83 |
| work_keys_str_mv | AT jenniferskchan variableselectionalgorithmforamixtureofpoissonregressionforhandlingoverdispersioninclaimsfrequencymodelingusingtelematicscardrivingdata AT stborischoy variableselectionalgorithmforamixtureofpoissonregressionforhandlingoverdispersioninclaimsfrequencymodelingusingtelematicscardrivingdata AT udimakov variableselectionalgorithmforamixtureofpoissonregressionforhandlingoverdispersioninclaimsfrequencymodelingusingtelematicscardrivingdata AT arielshamir variableselectionalgorithmforamixtureofpoissonregressionforhandlingoverdispersioninclaimsfrequencymodelingusingtelematicscardrivingdata AT veredshapovalov variableselectionalgorithmforamixtureofpoissonregressionforhandlingoverdispersioninclaimsfrequencymodelingusingtelematicscardrivingdata |