Machine Learning Methods to Perform Pricing Optimization: A Comparison with Standard Generalized Linear Models
Open accessAbstract
As the level of competition increases, pricing optimization is gaining a central role in most mature insurance markets, forcing insurers to optimize their rating and consider customer behavior; the modeling scene for the latter is one currently dominated by frameworks based on generalized linear models (GLMs). In this paper, we explore the applicability of novel machine learning techniques, such as tree-boosted models, to optimize the proposed premium on prospective policyholders. Given their predictive gain over GLMs, we carefully analyze both the advantages and disadvantages induced by their use.
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?
Competitive policies are not priced too expensively at other insurers, so it is relatively attractive to switch insurers.
“Similarly, competitive policies are not priced too expensively at other insurers, so it is relatively attractive to switch insurers (De la Llave et al., 2019;Leiria et al., 2021;Spedicato et al., 2018).”
From Customer price sensitivities in competitive insurance markets (2022) · cites this paper as Spedicato et al., 2018
The Introduction (page unavailable) says web aggregators make competing insurers’ quotes easier to compare and that customers may accept competitors’ deals. It does not establish that those policies are generally inexpensive or that switching insurers is relatively attractive. (LLM, conf=0.84)
Experimental — accuracy not yet measured
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · see citing works
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · see citing works
Cortes, C., & Vapnik, V. N. (1995) · Machine Learning · doi:10.1023/a:1022627411411 · Cited by 34,565 · see citing works
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
Regularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957 · see citing works
McCullagh, P., & Nelder, J. A. (1989) · doi:10.1007/978-1-4899-3242-6 · Cited by 16,836 · see citing works
An Analysis of Transformations
Box, G. E. P., & Cox, D. R. (1964) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.2517-6161.1964.tb00553.x · Cited by 15,059 · see citing works
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788 · see citing works
Zaharia, M., Xin, R., Wendell, P., Das, T., Armbrust, M., Dave, A., Meng, X., Rosen, J., Venkataraman, S., Franklin, M. J. M., et al. (2016) · Communications of the ACM · doi:10.1145/2934664 · Cited by 2,443 · see citing works
Discriminatory analysis: Nonparametric discrimination: Consistency properties
Fix, E., & Hodges, J. L. (1951) · PsycEXTRA Dataset · doi:10.1037/e471672008-001 · Cited by 1,731 · see citing works
Penalized Discriminant Analysis
Hastie, T., Buja, A., & Tibshirani, R. J. (1995) · The Annals of Statistics · doi:10.1214/aos/1176324456 · Cited by 872 · see citing works
Model-Based Recursive Partitioning
Zeileis, A., Hothorn, T., & Hornik, K. (2008) · Journal of Computational and Graphical Statistics · doi:10.1198/106186008x319331 · Cited by 771 · see citing works
Applying data mining to telecom churn management
Hung, S., Yen, D. C., & Wang, H.-Y. (2005) · Expert Systems with Applications · doi:10.1016/j.eswa.2005.09.080 · Cited by 518 · see citing works
Gradient boosting trees for auto insurance loss cost modeling and prediction
Guelman, L. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.09.058 · Cited by 247 · see citing works
Predictive Modeling Applications in Actuarial Science
(2014) · Cambridge University Press eBooks · doi:10.1017/cbo9781139342674 · Cited by 122 · see citing works
Random Forests for Uplift Modeling: An Insurance Customer Retention Case
Guelman, L., Guillén, M., & Pérez-Marín, A. M. (2012) · Lecture Notes in Business Information Processing · doi:10.1007/978-3-642-30433-0_13 · Cited by 61 · see citing works
A causal inference approach to measure price elasticity in Automobile Insurance
Guelman, L., & Guillén, M. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.07.059 · Cited by 43 · see citing works
Yeo, A. C., Smith‐Miles, K., Willis, R. J., & Brooks, M. (2001) · Lecture notes in computer science · doi:10.1007/3-540-45718-6_43 · Cited by 20 · see citing works
Estimating Insurance Attrition Using Survival Analysis
Fu, L., & Wang, H. (2014) · Variance · doi:10.66573/001c.120843 · Cited by 1 · see citing works
THE PRECISION OF DISCRIMINANT FUNCTIONS
FISHER, R. A. (1940) · Annals of Eugenics · doi:10.1111/j.1469-1809.1940.tb02264.x
Spatial Sign Preprocessing: A Simple Way To Impart Moderate Robustness to Multivariate Estimators
Serneels, S., Nolf, E. D., & Espen, P. J. V. (2006) · Journal of Chemical Information and Modeling · doi:10.1021/ci050498u
Flagged first, then by citations
Research works printed but not linked: 14
- Frees, E. W., G. Meyers, and R. A. Derrig, Predictive Modeling Applications in Actuarial Science: Volume 2, Case Studies in Insurance, International Series on Actuarial Science, New York: Cambridge University Press, 2016 .
- Guven, S., and M. McPhail, "Beyond the Cost Model: Under- standing Price Elasticity and Its Applications," Casualty Actuarial Society EForum, Spring 2013, pp. 1-29.
- Kuhn, M., "Optimization Methods for Tuning Predictive Models," paper presented to Cambridge (UK) R User Group, 2016.
- LeDell, E., S. Sapp, and M. van der Laan, "Subsemble: An Ensemble Method for Combining Subset-Specific Algorithm Fits," Journal of Applied Statistics, 41:6, 2014, pp. 1247-1259.
- Liaw, A., and M. Wiener, "Classification and Regression by Random Forest," R News 2:3, 2002, pp. 18-22. References
- Baribeau, A. G., "Price Optimization and the Descending Confusion," Actuarial Review, September/October 2015, pp. 30-33.
- Dal Pozzolo, A., G. Moro, and G. Bontempi, "Comparison of Data Mining Techniques for Insurance Claim Prediction," Master's thesis, University of Bologna, 2011.
- Dutang, C., "The Customer, the Insurer and the Market," Bulletin Français d'Actuariat 12:24, 2012, pp. 35-85.
- Wiley, J. F., 2016, R Deep Learning Essentials, Birmingham, UK: Packt Publishing Ltd.
- Marin, A., and T. Bayley, "Price Optimization for New Business Profit and Growth," Emphasis 2010 (1), pp. 18-22.
- Milhaud, X., S. Loisel, and V. Maume-Deschamps, "Surrender Trigger in Life Insurance: What Main Features Affect the Surrender Behaviors in a Classical Economic Context?," Bulletin Français d'Actuariat, 11:22, pp. 5-48, 2011.
- Nykodym, T., T. Kraljevic, N. Hussami, A. Rao, and A. Wang, Generalized Linear Modeling with H2O (5th ed.), Mountain View, CA: H2O.ai, 2016, https://h2o-release.s3.amazonaws. com/h2o/rel-turing/10/docs-website/h2o-docs/booklets/ GLMBooklet.pdf.
- Nykodym, T., A. Rao, A. Wang, T. Kraljevic, J. Lanford, and N. Hussami, Generalized Linear Modeling with H2O (3rd ed.), Mountain View, CA: H2O.ai, 2015, https://h2o-release.s3. amazonaws.com/h2o/rel-slater/9/docs-website/h2o-docs/ booklets/GLM_Vignette.pdf.
- Rish, I., 2001, "An Empirical Study of the Naive Bayes Clas- sifier," Proceedings of IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, 3, pp. 41-46.
Cited by
Sorted by citations
Li, W., & Hsu, C.-Y. (2022) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi11070385 · Cited by 147 · see citing works
Customer price sensitivities in competitive insurance markets
Verschuren, R. M. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117133 · Cited by 13 · see citing works
- Authors
- Spedicato, G., Dutang, C., & Petrini, L.
- Affiliations
- Unipol Group, Italy
- Université Paris Dauphine-PSL (FR)
- Virality
- Venue
- Variance
- Publisher
- Casualty Actuarial Society
- Published
- 2018-01-01
- Volume
- 12
- Issue
- 1
- ISSN
- 1940-6452 (ISSN-L)
- OpenAlex
- W7154608141
- Cited by
- 5
- References
- 21
- Citations by year
- 2026: 4 · 2022: 1
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Variance (publishedVersion)
- Funders
- Society of Actuaries
- Topics
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Insurance and Financial Risk Management
- Social Sciences › Decision Sciences › Management Science and Operations Research › Probability and Risk Models
- Social Sciences › Business, Management and Accounting › Marketing › Customer churn and segmentation
- Keywords
- price optimization, insurance rating, generalized linear models, customer behavior modeling, model comparison
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
