COST-SENSITIVE MULTI-CLASS ADABOOST FOR UNDERSTANDING DRIVING BEHAVIOR BASED ON TELEMATICS
- 31 August 2021
- journal article
- research article
- Published by Cambridge University Press (CUP) in ASTIN Bulletin
- Vol. 51 (3), 719-751
- https://doi.org/10.1017/asb.2021.22
Abstract
Using telematics technology, insurers are able to capture a wide range of data to better decode driver behavior, such as distance traveled and how drivers brake, accelerate, or make turns. Such additional information also helps insurers improve risk assessments for usage-based insurance, a recent industry innovation. In this article, we explore the integration of telematics information into a classification model to determine driver heterogeneity. For motor insurance during a policy year, we typically observe a large proportion of drivers with zero accidents, a lower proportion with exactly one accident, and a far lower proportion with two or more accidents. We here introduce a cost-sensitive multi-class adaptive boosting (AdaBoost) algorithm we call SAMME.C2 to handle such class imbalances. We calibrate the algorithm using empirical data collected from a telematics program in Canada and demonstrate an improved assessment of driving behavior using telematics compared with traditional risk variables. Using suitable performance metrics, we show that our algorithm outperforms other learning models designed to handle class imbalances.Keywords
This publication has 32 references indexed in Scilit:
- Boosting Algorithms: A Review of Methods, Theory, and ApplicationsPublished by Springer Science and Business Media LLC ,2012
- Genetic Programming for Classification with Unbalanced DataLecture Notes in Computer Science, 2010
- Multi-class AdaBoostStatistics and Its Interface, 2009
- Cost-sensitive boosting for classification of imbalanced dataPattern Recognition, 2007
- 10 CHALLENGING PROBLEMS IN DATA MINING RESEARCHInternational Journal of Information Technology & Decision Making, 2006
- SMOTEBoost: Improving Prediction of the Minority Class in BoostingLecture Notes in Computer Science, 2003
- Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)The Annals of Statistics, 2000
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Reducing Misclassification CostsPublished by Elsevier BV ,1994
- A Method for Comparing Two Hierarchical ClusteringsJournal of the American Statistical Association, 1983