Stochastic gradient boosting frequency-severity model of insurance claims
Open accessAbstract
The standard GLM and GAM frequency-severity models assume independence between the claim frequency and severity. To overcome restrictions of linear or additive forms and to relax the independence assumption, we develop a data-driven dependent frequency-severity model, where we combine a stochastic gradient boosting algorithm and a profile likelihood approach to estimate parameters for both of the claim frequency and average claim severity distributions, and where we introduce the dependence between the claim frequency and severity by treating the claim frequency as a predictor in the regression model for the average claim severity. The model can flexibly capture the nonlinear relation between the claim frequency (severity) and predictors and complex interactions among predictors and can fully capture the nonlinear dependence between the claim frequency and severity. A simulation study shows excellent prediction performance of our model. Then, we demonstrate the application of our model with a French auto insurance claim data. The results show that our model is superior to other state-of-the-art models.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
For both claim frequency and claim severity models, a grid search procedure was used to calibrate boosting and decision tree-specific hyperparameters.
“For both the claim frequency and claim severity models, a grid search procedure was used to calibrate the boosting and the decision tree-specific hyperparameters (Su and Bai 2020).”
From Modelling Motor Insurance Claim Frequency and Severity Using Gradient Boosting (2023) · cites this paper as Su and Bai 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · see citing works
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162 · see citing works
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 21,028 · see citing works
A decision-theoretic generalization of on-line learning and an application to boosting
Freund, Y., & Schapire, R. E. (1997) · Journal of Computer and System Sciences · doi:10.1006/jcss.1997.1504 · Cited by 20,466 · see citing works
Generalized Additive Models: An Introduction with R
Wood, S. N. (2017) · doi:10.1201/9781315370279 · Cited by 13,852 · see citing works
Hastie, T., & Tibshirani, R. (1986) · Statistical Science · doi:10.1214/ss/1177013604 · Cited by 12,575 · see citing works
Friedman, J. H. (2002) · Computational Statistics & Data Analysis · doi:10.1016/s0167-9473(01)00065-2 · Cited by 7,067 · see citing works
Friedman, J., Hastie, T., & Tibshirani, R. (2000) · The Annals of Statistics · doi:10.1214/aos/1016218223 · Cited by 6,884 · see citing works
Wood, S. N. (2006) · doi:10.1201/9781420010404 · Cited by 4,953 · see citing works
Generalized additive models for medical research
Hastie, T. J., & Tibshirani, R. J. (1995) · Statistical Methods in Medical Research · doi:10.1177/096228029500400302 · Cited by 1,275 · see citing works
Arcing classifier (with discussion and a rejoinder by the author)
Breiman, L. (1998) · The Annals of Statistics · doi:10.1214/aos/1024691079 · Cited by 1,104 · see citing works
Prediction Games and Arcing Algorithms
Breiman, L. (1999) · Neural Computation · doi:10.1162/089976699300016106 · Cited by 530 · see citing works
Testing for Evidence of Adverse Selection in the Automobile Insurance Market: A Comment
Dionne, G., Gouriéroux, C., & Vanasse, C. (2001) · Journal of Political Economy · doi:10.1086/319557 · Cited by 257 · see citing works
Chen, F., Chen, S., & Ma, X. (2018) · Journal of Safety Research · doi:10.1016/j.jsr.2018.02.010 · Cited by 206 · see citing works
A multivariate tobit analysis of highway accident-injury-severity rates
Anastasopoulos, P. C., Shankar, V. N., Haddock, J. E., & Mannering, F. (2011) · Accident Analysis & Prevention · doi:10.1016/j.aap.2011.11.006 · Cited by 193 · see citing works
Chen, F., Song, M., & Ma, X. (2019) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph16142632 · Cited by 177 · see citing works
A Bias Correction Algorithm for the Gini Variable Importance Measure in Classification Trees
Sandri, M. F., & Zuccolotto, P. (2008) · Journal of Computational and Graphical Statistics · doi:10.1198/106186008x344522 · Cited by 166 · see citing works
Multivariate random parameters collision count data models with spatial heterogeneity
Barua, S., El‐Basyouny, K., & Islam, M. T. (2015) · Analytic Methods in Accident Research · doi:10.1016/j.amar.2015.11.002 · Cited by 151 · see citing works
Macro and micro models for zonal crash prediction with application in hot zones identification
Huang, H., Song, B., Xu, P., Zeng, Q., Lee, J. J., & Abdel-Aty, M. A. (2016) · Journal of Transport Geography · doi:10.1016/j.jtrangeo.2016.06.012 · Cited by 132 · see citing works
Generalized linear models for dependent frequency and severity of insurance claims
Garrido, J., Genest, C., & Schulz, J. (2016) · Insurance: Mathematics and Economics · doi:10.1016/j.insmatheco.2016.06.006 · Cited by 131 · see citing works
A mixed copula model for insurance claims and claim sizes
Czado, C., Kastenmeier, R., Brechmann, E. C., & Min, A. (2011) · Scandinavian Actuarial Journal · doi:10.1080/03461238.2010.546147 · Cited by 125 · see citing works
Dong, B., Ma, X., Chen, F., & Chen, S. (2018) · Journal of Advanced Transportation · doi:10.1155/2018/2702360 · Cited by 123 · see citing works
A multivariate random-parameters Tobit model for analyzing highway crash rates by injury severity
Zeng, Q., Wen, H., Huang, H., Pei, X., & Wong, S. C. (2016) · Accident Analysis & Prevention · doi:10.1016/j.aap.2016.11.018 · Cited by 117 · see citing works
Multivariate spatial models of excess crash frequency at area level: Case of Costa Rica
Agüero-Valverde, J. (2013) · Accident Analysis & Prevention · doi:10.1016/j.aap.2013.06.014 · Cited by 110 · see citing works
Insurance Premium Prediction via Gradient Tree-Boosted Tweedie Compound Poisson Models
Yang, Y. A., Qian, W., & Zou, H. (2016) · Journal of Business and Economic Statistics · doi:10.1080/07350015.2016.1200981 · Cited by 100 · see citing works
Grabit: Gradient tree-boosted Tobit models for default prediction
Sigrist, F., & Hirnschall, C. (2019) · Journal of Banking & Finance · doi:10.1016/j.jbankfin.2019.03.004 · Cited by 98 · see citing works
Summarizing Insurance Scores Using a Gini Index
Frees, E. W., Meyers, G., & Cummings, A. D. (2011) · Journal of the American Statistical Association · doi:10.1198/jasa.2011.tm10506 · Cited by 96 · cited 2× · see citing works
“We compare the models by using a Gini index to measure the discrepancy between the premium and loss distributions (Frees, Meyers, and Cummings [36, 37]).”
MethodSpatial modelling of claim frequency and claim size in non-life insurance
Gschlößl, S., & Czado, C. (2007) · Scandinavian Actuarial Journal · doi:10.1080/03461230701414764 · Cited by 96 · see citing works
Dependent frequency–severity modeling of insurance claims
Shi, P., Feng, X., & Ivantsova, A. (2015) · Insurance Mathematics and Economics · doi:10.1016/j.insmatheco.2015.07.006 · Cited by 89 · see citing works
Zeng, Q., Guo, Q., Wong, S. C., Wen, H., Huang, H., & Pei, X. (2019) · Transportmetrica A Transport Science · doi:10.1080/23249935.2019.1652867 · Cited by 85 · see citing works
Insurance Ratemaking and a Gini Index
Frees, E. W., Meyers, G. G., & Cummings, A. D. (2013) · Journal of Risk & Insurance · doi:10.1111/j.1539-6975.2012.01507.x · Cited by 83 · see citing works
Predicting the frequency and amount of health care expenditures
Frees, E. W., Gao, J., & Rosenberg, M. A. (2011) · North American Actuarial Journal · doi:10.1080/10920277.2011.10597626 · Cited by 73 · see citing works
Total loss estimation using copula-based regression models
Krämer, N., Brechmann, E., Silvestrini, D., & Czado, C. (2013) · Insurance Mathematics and Economics · doi:10.1016/j.insmatheco.2013.09.003 · Cited by 71 · see citing works
Actuarial Applications of a Hierarchical Insurance Claims Model
Frees, E. W., Shi, P., & Valdez, E. A. (2009) · Astin Bulletin · doi:10.2143/ast.39.1.2038061 · Cited by 71 · see citing works
Zeng, Q., Wen, H., Wong, S. C., Huang, H., Guo, Q., & Pei, X. (2018) · Journal of Transportation Safety & Security · doi:10.1080/19439962.2018.1516259 · Cited by 59 · see citing works
Case Study: French Motor Third-Party Liability ClaimsPreprint
Noll, A., Salzmann, R., & Wüthrich, M. V. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3164764 · Cited by 58 · see citing works
Sandri, M. F., & Zuccolotto, P. (2009) · Statistics and Computing · doi:10.1007/s11222-009-9132-0 · Cited by 57 · see citing works
Kriegler, B., & Berk, R. (2010) · The Annals of Applied Statistics · doi:10.1214/10-aoas328 · Cited by 53 · see citing works
Tweedie gradient boosting for extremely unbalanced zero-inflated data
Zhou, H., Qian, W., & Yang, Y. A. (2020) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2020.1772302 · Cited by 39 · see citing works
Modeling dependent yearly claim totals including zero claims in private health insurance
Erhardt, V., & Czado, C. (2010) · Scandinavian Actuarial Journal · doi:10.1080/03461238.2010.489762 · Cited by 30 · see citing works
Generalization of boosting algorithms and applications of bayesian inference for massive datasets
Ridgeway, G. K., Madigan, D., & Richardson, T. (1999) · ResearchWorks at the University of Washington (University of Washington) · Cited by 9 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Modelling Motor Insurance Claim Frequency and Severity Using Gradient Boosting
Clemente, C., Guerreiro, G. R., & Bravo, J. M. (2023) · Risks · doi:10.3390/risks11090163 · Cited by 28 · see citing works
A data science approach to risk assessment for automobile insurance policies
Hosein, P. A. (2023) · International Journal of Data Science and Analytics · doi:10.1007/s41060-023-00392-x · Cited by 25 · see citing works
Esmaeili, N., Saraei, F. E. K., Pirbazari, A. E., Tabatabai‐Yazdi, F., Khodaee, Z., Amirinezhad, A., Esmaeili, A., & Pirbazari, A. E. (2022) · Chemical Product and Process Modeling · doi:10.1515/cppm-2021-0065 · Cited by 11 · see citing works
Amiroch, S., Irawan, M. I., Mukhlash, I., Faroby, M. H. Z. A., & Nidom, C. A. (2022) · Symmetry · doi:10.3390/sym14061114 · Cited by 9 · see citing works
Li, W., Li, S., Brown, T. C., Sun, Q., Wang, X., Yakovlev, V. V., Kealy, A., Moran, B., & Greentree, A. D. (2023) · AVS Quantum Science · doi:10.1116/5.0162501 · Cited by 4 · see citing works
Reiff, M., Šoltés, E., Komara, S., Šoltésová, T., & Zelinová, S. (2022) · Equilibrium Quarterly Journal of Economics and Economic Policy · doi:10.24136/eq.2022.028 · Cited by 3 · see citing works
Tang, N., Liu, S., Li, K., Zhou, Q., Dai, Y., Sun, H., Zhang, Q., Ji, H., & Qi, C. (2024) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2024.1419551 · Cited by 3 · see citing works
A Data-Driven Pricing Strategy for Automobile Insurance Policies
Hosein, P. A. (2022) · Asia Conference on Machine Learning and Computing (ACMLC) · doi:10.1109/acmlc58173.2022.00009 · Cited by 2 · see citing works
Predictive modeling for claims in automobile insurance
Marciuc, M. A. (2024) · Virgil Madgearu Review of Economic Studies and Research · doi:10.24193/rvm.2024.17.118 · Cited by 2 · see citing works
Faroby, M. H. Z. A., Fadhilah, H. N., Amiroch, S., & Hidayat, R. S. (2022) · Kinetik Game Technology Information System Computer Network Computing Electronics and Control · doi:10.22219/kinetik.v7i2.1424 · Cited by 2 · see citing works
Predicting Automobile Insurance Claim Rate Versus Through Severity and Frequency Predictions
Moonoo, D., & Hosein, P. A. (2024) · IEEE International Conference on Technology Management, Operations and Decisions (ICTMOD) · doi:10.1109/ictmod63116.2024.10878218 · Cited by 1 · see citing works
Implementing Custom Loss Functions in Advanced Machine Learning Structures for Targeted Outcomes
Hitchen, T., & Nadarajah, S. (2025) · Journal of risk and financial management · doi:10.3390/jrfm18070348 · Cited by 1 · see citing works
Gradient Boosting in Motor Insurance Claim Frequency Modelling
Clemente, C., Guerreiro, G. R., & Bravo, J. M. (2023) · Conferência da Associação Portuguesa de Sistemas de Informação (CAPSI) · doi:10.18803/capsi.v23.53-69 · Cited by 1 · see citing works
Sun, T., Wang, H., & Wang, D. (2024) · Computational Economics · doi:10.1007/s10614-024-10574-9 · Cited by 1 · see citing works
Predicting Components of a Target Value Versus Predicting the Target Value Directly
Sooklal, S., & Hosein, P. A. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-66705-3_24 · Cited by 1 · see citing works
Ibrahim, J., Stanley, J., Murfi, H., Novkaniza, F., & Devila, S. (2024) · International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) · doi:10.1109/icicyta64807.2024.10912952 · Cited by 1 · see citing works
A Neural Frequency-Severity Model and Its Application to Insurance ClaimsPreprint
Lim, D. (2021) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2106.10770
Guillen, Vidal-Llana, X., & Guillén, M. (2020) · Anales del Instituto de Actuarios Españoles · doi:10.26360/2020_7
Application of GLM and GAMLSS Models in Predictive Analysis of Motor Bodily Injury Claims
Brati, E. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-67431-0_35
Conformal prediction for frequency-severity modeling
Graziadei, H., F., P. C. M., de Melo, E. F. L., & Targino, R. S. (2025) · Journal of Applied Statistics · doi:10.1080/02664763.2025.2567988 · Cited by 2 · see citing works
Credit Card Fraud Detection in the Era of Digital Finance a Comparative Machine Learning Approach
Hardayani, B. D. K., & Widiantoro, A. D. (2025) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic68054.2025.11309420
Israni, T., Daly, L., Condon, J., & Wolsztynski, E. (2026) · British Actuarial Journal · doi:10.1017/s1357321725100317
Motor insurance data analysis by quantum machine learning
Tamturk, M., Ginossar, E., Carenzo, M., & Perret, C. (2026) · Discover Quantum Science · doi:10.1007/s44464-026-00007-x
Zhang, F., Wang, B., Liu, X., & Du, W. (2026) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2026.109937
- Authors
- Su, X., & Bai, M.
- Affiliations
- Beihang University (CN)
- Corresponding author
- Su, Xiaoshan
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2020-08-31
- Volume
- 15
- Issue
- 8
- Pages
- e0238000
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC7458339
- OpenAlex
- W3082368934
- Cited by
- 24
- References
- 41
- Citations by year
- 2026: 3 · 2025: 3 · 2024: 7 · 2023: 4 · 2022: 5 · 2021: 1 · 2020: 1
- FWCI
- 1.75
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (71333014, 71571007)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Probability and Risk Models
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Insurance and Financial Risk Management
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Keywords
- insurance claims, stochastic gradient boosting, profile likelihood, nonlinear dependence, automobile insurance
- MeSH terms
- Insurance Claim Review, Stochastic Processes, Models, Statistical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
