Statistical and Machine Learning Methods for Auto Insurance Claims Prediction: A Survey
Resumo
This paper reviews statistical and machine-learning methods for predicting claim frequency, claim severity, and loss cost in auto insurance. We cover generalized regression models, tree ensembles, distributional methods, neural and hybrid models, and attention-based architectures. The review compares datasets, targets, validation strategies, and empirical findings, with emphasis on exposure treatment, calibration, uncertainty, interpretability, and temporal validation. We also discuss open challenges related to benchmark scarcity, portfolio drift, high-cardinality variables, joint frequency-severity modeling, and the responsible use of telematics, text, and multimodal data.Referências
Blier-Wong, C., Cossette, H., Lamontagne, L., and Marceau, E. (2021). Machine learning in p&c insurance: A review for pricing and reserving. Risks, 9(1):4.
Brauer, A. (2024). Enhancing actuarial non-life pricing models via transformers. European Actuarial Journal, 14:991–1012.
Cameron, A. C. and Trivedi, P. K. (2013). Regression Analysis of Count Data. Number 53 in Econometric Society Monographs. Cambridge University Press, Cambridge, 2 edition.
Chevalier, D. and Côté, M.-P. (2025). From point to probabilistic gradient boosting for claim frequency and severity prediction. European Actuarial Journal, 15:707–752.
de Jong, P. and Heller, G. Z. (2008). Generalized Linear Models for Insurance Data. International Series on Actuarial Science. Cambridge University Press, Cambridge.
Duan, T., Avati, A., Ding, D. Y., Thai, K. K., Basu, S., Ng, A., and Schuler, A. (2020). NGBoost: Natural gradient boosting for probabilistic prediction. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 2690–2700. PMLR.
Dugas, C., Bengio, Y., Chapados, N., Vincent, P., Denoncourt, G., and Fournier, C. (2003). Statistical learning algorithms applied to automobile insurance ratemaking. In Shapiro, A. F. and Jain, L. C., editors, Intelligent and Other Computational Techniques in Insurance: Theory and Applications, pages 137–197. World Scientific.
Frees, E. W., Derrig, R. A., and Meyers, G., editors (2014). Predictive Modeling Applications in Actuarial Science: Volume I, Predictive Modeling Techniques. International Series on Actuarial Science. Cambridge University Press, Cambridge.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5):1189–1232.
Fujita, S., Tanaka, T., Kondo, K., and Iwasawa, H. (2020). AGLM: A hybrid modeling method of GLM and data science techniques. Technical report, Actuarial Colloquium Paris.
Gao, G. (2024). Fitting Tweedie’s compound poisson model to pure premium with the EM algorithm. Insurance: Mathematics and Economics, 114:29–42.
Gneiting, T. and Raftery, A. E. (2007). Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102(477):359–378.
Gorishniy, Y., Rubachev, I., Khrulkov, V., and Babenko, A. (2021). Revisiting deep learning models for tabular data. In Advances in Neural Information Processing Systems, volume 34 of NeurIPS. arXiv:2106.11959.
Guelman, L. (2012). Gradient boosting trees for auto insurance loss cost modeling and prediction. Expert Systems with Applications, 39(3):3659–3667.
Hanafy, M. and Ming, R. (2021). Machine learning approaches for auto insurance big data. Risks, 9(2):42.
Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, volume 2. Springer.
Hastie, T. J. and Tibshirani, R. J. (1990). Generalized Additive Models. Monographs on Statistics and Applied Probability. Chapman and Hall, London.
He, H. and Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9):1263–1284.
Henckaerts, R. and Antonio, K. (2022). The added value of dynamically updating motor insurance prices with telematics collected driving behavior data. Insurance: Mathematics and Economics, 105:79–95.
Henckaerts, R., Côté, M.-P., Antonio, K., and Verbelen, R. (2021). Boosting insights in insurance tariff plans with tree-based machine learning methods. North American Actuarial Journal, 25(2):255–285.
Holvoet, F., Antonio, K., and Henckaerts, R. (2025). Neural networks for insurance pricing with frequency and severity data: A benchmark study from data preprocessing to technical tariff. North American Actuarial Journal, pages 1–44.
Huang, X., Khetan, A., Cvitkovic, M., and Karnin, Z. S. (2020). TabTransformer: Tabular data modeling using contextual embeddings. arXiv:2012.06678.
Ibrahim, J., Murfi, H., Novkaniza, F., and Pramono, A. (2025). Rethinking the interpretability of XGBoost for insurance pricing: A case study on motor third-party liability insurance. SSRN preprint.
Jørgensen, B. (1997). The Theory of Dispersion Models. Chapman & Hall/CRC Monographs on Statistics & Applied Probability. Chapman & Hall/CRC, London.
Lambert, D. (1992). Zero-inflated poisson regression, with an application to defects in manufacturing. Technometrics, 34(1):1–14.
Li, Y. et al. (2025). SurvFormer: A transformer based framework for survival analysis in insurance underwriting. In Companion Proceedings of the Web Conference 2025. ACM.
Lindholm, M. and Palmquist, J. (2024). Black-box guided generalised linear model building with non-life pricing applications. Annals of Actuarial Science, 18(3):675–691.
März, A. and Kneib, T. (2022). Distributional gradient boosting machines. arXiv:2204.00778.
McDonnell, K., Murphy, F., Sheehan, B., Masello, L., and Castignani, G. (2023). Deep learning in insurance: Accuracy and model interpretability using TabNet. Expert Systems with Applications, 217:119543.
McKinsey Company (2025). The state of AI. Online report. Accessed 10 July 2025.
McNeil, A. J., Frey, R., and Embrechts, P. (2015). Quantitative Risk Management: Concepts, Techniques and Tools. Princeton University Press, Princeton, NJ.
Meinshausen, N. (2006). Quantile regression forests. Journal of Machine Learning Research, 7:983–999.
Micci-Barreca, D. (2001). A preprocessing scheme for high-cardinality categorical attributes in classification and prediction problems. SIGKDD Explorations, 3(1):27–32.
Mullahy, J. (1986). Specification and testing of some modified count data models. Journal of Econometrics, 33(3):341–365.
Nelder, J. A. and Wedderburn, R. W. M. (1972). Generalized linear models. Journal of the Royal Statistical Society. Series A (General), 135(3):370–384.
Poufinas, T., Gogas, P., Papadimitriou, T., and Zaganidis, E. (2023). Machine learning in forecasting motor insurance claims. Risks, 11(9):164.
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., and Gulin, A. (2018). Cat-Boost: Unbiased boosting with categorical features. In Advances in Neural Information Processing Systems, volume 31. arXiv:1706.09516.
Richman, R., Scognamiglio, S., and Wüthrich, M. V. (2025). The credibility transformer. European Actuarial Journal, 15:345–379.
Rigby, R. A. and Stasinopoulos, D. M. (2005). Generalized additive models for location, scale and shape. Journal of the Royal Statistical Society: Series C (Applied Statistics), 54(3):507–554.
Saito, T. and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE, 10(3):e0118432.
Smyth, G. K. and Jørgensen, B. (2002). Fitting Tweedie’s compound poisson model to insurance claims data: Dispersion modelling. ASTIN Bulletin, 32(1):143–157.
So, B. and Valdez, E. A. (2024). Zero-inflated Tweedie boosted trees with CatBoost for insurance loss analytics. arXiv:2406.16206.
Sprangers, O., Schelter, S., and de Rijke, M. (2021). Probabilistic gradient boosting machines for large-scale probabilistic regression. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
Su, X. and Bai, M. (2020). Stochastic gradient boosting frequency-severity model of insurance claims. PLOS ONE, 15(8):e0238000.
Sun, T., Yang, J., Li, J., Chen, J. Y., Liu, M., Fan, L., and Wang, X. (2024). Enhancing auto insurance risk evaluation with transformer and SHAP. IEEE Access.
Troxler, A. and Schelldorfer, J. (2024). Actuarial applications of natural language processing using transformers: Case studies for using text features in an actuarial context. British Actuarial Journal, 29:e4.
Verbelen, R., Antonio, K., and Claeskens, G. (2018). Unravelling the predictive power of telematics in car insurance pricing. Journal of the Royal Statistical Society: Series C (Applied Statistics), 67(5):1275–1304.
Wilson, A. A., Nehme, A., Dhyani, A., and Mahbub, K. (2024). A comparison of generalised linear modelling with machine learning approaches for predicting loss cost in motor insurance. Risks, 12(4):62.
Wüthrich, M. V. and Merz, M. (2023). Statistical Foundations of Actuarial Learning and its Applications. Springer Actuarial. Springer Nature Switzerland AG, Cham.
Xu, S., Manathunga, V., and Hong, D. (2023). Framework of bert-based nlp models for frequency and severity in insurance claims. Variance, 16(2).
Yang, J., Chen, K., Ding, K., Na, C., Wang, M., et al. (2023). Auto insurance fraud detection with multimodal learning. Data Intelligence, 5(2):388–412.
Yang, Y., Qian, W., and Zou, H. (2018). Insurance premium prediction via gradient tree-boosted Tweedie compound poisson models. Journal of Business & Economic Statistics, 36(3):456–470.
Ye, C., Zhang, L., Han, M., Yu, Y., Zhao, B., and Yang, Y. (2022). Combining predictions of auto insurance claims. Econometrics, 10(2):19.
Zhou, H., Yang, Y., and Qian, W. (2022). Tweedie gradient boosting for extremely unbalanced zero-inflated data. Communications in Statistics – Simulation and Computation.
Brauer, A. (2024). Enhancing actuarial non-life pricing models via transformers. European Actuarial Journal, 14:991–1012.
Cameron, A. C. and Trivedi, P. K. (2013). Regression Analysis of Count Data. Number 53 in Econometric Society Monographs. Cambridge University Press, Cambridge, 2 edition.
Chevalier, D. and Côté, M.-P. (2025). From point to probabilistic gradient boosting for claim frequency and severity prediction. European Actuarial Journal, 15:707–752.
de Jong, P. and Heller, G. Z. (2008). Generalized Linear Models for Insurance Data. International Series on Actuarial Science. Cambridge University Press, Cambridge.
Duan, T., Avati, A., Ding, D. Y., Thai, K. K., Basu, S., Ng, A., and Schuler, A. (2020). NGBoost: Natural gradient boosting for probabilistic prediction. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 2690–2700. PMLR.
Dugas, C., Bengio, Y., Chapados, N., Vincent, P., Denoncourt, G., and Fournier, C. (2003). Statistical learning algorithms applied to automobile insurance ratemaking. In Shapiro, A. F. and Jain, L. C., editors, Intelligent and Other Computational Techniques in Insurance: Theory and Applications, pages 137–197. World Scientific.
Frees, E. W., Derrig, R. A., and Meyers, G., editors (2014). Predictive Modeling Applications in Actuarial Science: Volume I, Predictive Modeling Techniques. International Series on Actuarial Science. Cambridge University Press, Cambridge.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5):1189–1232.
Fujita, S., Tanaka, T., Kondo, K., and Iwasawa, H. (2020). AGLM: A hybrid modeling method of GLM and data science techniques. Technical report, Actuarial Colloquium Paris.
Gao, G. (2024). Fitting Tweedie’s compound poisson model to pure premium with the EM algorithm. Insurance: Mathematics and Economics, 114:29–42.
Gneiting, T. and Raftery, A. E. (2007). Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102(477):359–378.
Gorishniy, Y., Rubachev, I., Khrulkov, V., and Babenko, A. (2021). Revisiting deep learning models for tabular data. In Advances in Neural Information Processing Systems, volume 34 of NeurIPS. arXiv:2106.11959.
Guelman, L. (2012). Gradient boosting trees for auto insurance loss cost modeling and prediction. Expert Systems with Applications, 39(3):3659–3667.
Hanafy, M. and Ming, R. (2021). Machine learning approaches for auto insurance big data. Risks, 9(2):42.
Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, volume 2. Springer.
Hastie, T. J. and Tibshirani, R. J. (1990). Generalized Additive Models. Monographs on Statistics and Applied Probability. Chapman and Hall, London.
He, H. and Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9):1263–1284.
Henckaerts, R. and Antonio, K. (2022). The added value of dynamically updating motor insurance prices with telematics collected driving behavior data. Insurance: Mathematics and Economics, 105:79–95.
Henckaerts, R., Côté, M.-P., Antonio, K., and Verbelen, R. (2021). Boosting insights in insurance tariff plans with tree-based machine learning methods. North American Actuarial Journal, 25(2):255–285.
Holvoet, F., Antonio, K., and Henckaerts, R. (2025). Neural networks for insurance pricing with frequency and severity data: A benchmark study from data preprocessing to technical tariff. North American Actuarial Journal, pages 1–44.
Huang, X., Khetan, A., Cvitkovic, M., and Karnin, Z. S. (2020). TabTransformer: Tabular data modeling using contextual embeddings. arXiv:2012.06678.
Ibrahim, J., Murfi, H., Novkaniza, F., and Pramono, A. (2025). Rethinking the interpretability of XGBoost for insurance pricing: A case study on motor third-party liability insurance. SSRN preprint.
Jørgensen, B. (1997). The Theory of Dispersion Models. Chapman & Hall/CRC Monographs on Statistics & Applied Probability. Chapman & Hall/CRC, London.
Lambert, D. (1992). Zero-inflated poisson regression, with an application to defects in manufacturing. Technometrics, 34(1):1–14.
Li, Y. et al. (2025). SurvFormer: A transformer based framework for survival analysis in insurance underwriting. In Companion Proceedings of the Web Conference 2025. ACM.
Lindholm, M. and Palmquist, J. (2024). Black-box guided generalised linear model building with non-life pricing applications. Annals of Actuarial Science, 18(3):675–691.
März, A. and Kneib, T. (2022). Distributional gradient boosting machines. arXiv:2204.00778.
McDonnell, K., Murphy, F., Sheehan, B., Masello, L., and Castignani, G. (2023). Deep learning in insurance: Accuracy and model interpretability using TabNet. Expert Systems with Applications, 217:119543.
McKinsey Company (2025). The state of AI. Online report. Accessed 10 July 2025.
McNeil, A. J., Frey, R., and Embrechts, P. (2015). Quantitative Risk Management: Concepts, Techniques and Tools. Princeton University Press, Princeton, NJ.
Meinshausen, N. (2006). Quantile regression forests. Journal of Machine Learning Research, 7:983–999.
Micci-Barreca, D. (2001). A preprocessing scheme for high-cardinality categorical attributes in classification and prediction problems. SIGKDD Explorations, 3(1):27–32.
Mullahy, J. (1986). Specification and testing of some modified count data models. Journal of Econometrics, 33(3):341–365.
Nelder, J. A. and Wedderburn, R. W. M. (1972). Generalized linear models. Journal of the Royal Statistical Society. Series A (General), 135(3):370–384.
Poufinas, T., Gogas, P., Papadimitriou, T., and Zaganidis, E. (2023). Machine learning in forecasting motor insurance claims. Risks, 11(9):164.
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., and Gulin, A. (2018). Cat-Boost: Unbiased boosting with categorical features. In Advances in Neural Information Processing Systems, volume 31. arXiv:1706.09516.
Richman, R., Scognamiglio, S., and Wüthrich, M. V. (2025). The credibility transformer. European Actuarial Journal, 15:345–379.
Rigby, R. A. and Stasinopoulos, D. M. (2005). Generalized additive models for location, scale and shape. Journal of the Royal Statistical Society: Series C (Applied Statistics), 54(3):507–554.
Saito, T. and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE, 10(3):e0118432.
Smyth, G. K. and Jørgensen, B. (2002). Fitting Tweedie’s compound poisson model to insurance claims data: Dispersion modelling. ASTIN Bulletin, 32(1):143–157.
So, B. and Valdez, E. A. (2024). Zero-inflated Tweedie boosted trees with CatBoost for insurance loss analytics. arXiv:2406.16206.
Sprangers, O., Schelter, S., and de Rijke, M. (2021). Probabilistic gradient boosting machines for large-scale probabilistic regression. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
Su, X. and Bai, M. (2020). Stochastic gradient boosting frequency-severity model of insurance claims. PLOS ONE, 15(8):e0238000.
Sun, T., Yang, J., Li, J., Chen, J. Y., Liu, M., Fan, L., and Wang, X. (2024). Enhancing auto insurance risk evaluation with transformer and SHAP. IEEE Access.
Troxler, A. and Schelldorfer, J. (2024). Actuarial applications of natural language processing using transformers: Case studies for using text features in an actuarial context. British Actuarial Journal, 29:e4.
Verbelen, R., Antonio, K., and Claeskens, G. (2018). Unravelling the predictive power of telematics in car insurance pricing. Journal of the Royal Statistical Society: Series C (Applied Statistics), 67(5):1275–1304.
Wilson, A. A., Nehme, A., Dhyani, A., and Mahbub, K. (2024). A comparison of generalised linear modelling with machine learning approaches for predicting loss cost in motor insurance. Risks, 12(4):62.
Wüthrich, M. V. and Merz, M. (2023). Statistical Foundations of Actuarial Learning and its Applications. Springer Actuarial. Springer Nature Switzerland AG, Cham.
Xu, S., Manathunga, V., and Hong, D. (2023). Framework of bert-based nlp models for frequency and severity in insurance claims. Variance, 16(2).
Yang, J., Chen, K., Ding, K., Na, C., Wang, M., et al. (2023). Auto insurance fraud detection with multimodal learning. Data Intelligence, 5(2):388–412.
Yang, Y., Qian, W., and Zou, H. (2018). Insurance premium prediction via gradient tree-boosted Tweedie compound poisson models. Journal of Business & Economic Statistics, 36(3):456–470.
Ye, C., Zhang, L., Han, M., Yu, Y., Zhao, B., and Yang, Y. (2022). Combining predictions of auto insurance claims. Econometrics, 10(2):19.
Zhou, H., Yang, Y., and Qian, W. (2022). Tweedie gradient boosting for extremely unbalanced zero-inflated data. Communications in Statistics – Simulation and Computation.
Publicado
19/10/2026
Como Citar
KENUPP, Yara S.; CASTRO, Paulo Andre L..
Statistical and Machine Learning Methods for Auto Insurance Claims Prediction: A Survey. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 623-634.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.30063.
