{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T17:27:14Z","timestamp":1788542834104,"version":"build-2803163510"},"reference-count":50,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>This paper proposes a novel methodology, based on machine learning and statistical models, for predicting hurricane-related losses to specific assets. Our approach uses three critical storm parameters typically tracked by meteorological agencies: maximum wind speed, minimum sea level pressure, and radius of maximum wind. The system categorizes potential damage events into three insurance-relevant classes: non-payable, partially payable, and fully payable. Three triggers for final payouts were designed: hybrid framework, standalone regression, and standalone non-linear regression. The hybrid framework combines two classification models and a non-linear regression model in an ensemble specifically designed to minimize the absolute differences between predicted and actual payouts (Total Absolute Error or TAE), addressing highly imbalanced and partially compensable events. Although this complex approach may not be suitable for all current contracts due to limited interpretability, it provides an approximate lower bound for the minimization of the absolute error. The standalone non-linear regression model is structurally simpler, yet it likewise offers limited transparency. This hybrid framework is not intended for direct deployment in parametric insurance contracts, but rather serves as a benchmarking and research tool to quantify the achievable reduction in basis risk under highly imbalanced conditions. The standalone linear regression provides an interpretable linear regression model optimized for feature selection and interaction terms, enabling direct deployment in parametric insurance contracts while maintaining transparency. These three approaches allow analysis of the trade-off between model complexity, predictive performance, and interpretability. The three approaches are compared using comprehensive hurricane simulation data from an industry-standard catastrophe model. The methodology is particularly valuable for parametric insurance applications, where rapid assessment and claims settlement are essential.<\/jats:p>","DOI":"10.3390\/a19010015","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:57:18Z","timestamp":1766487438000},"page":"15","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Hybrid Machine Learning Framework for Predicting Hurricane Losses in Parametric Insurance with Highly Imbalanced Data"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5226-0726","authenticated-orcid":false,"given":"Yangchongyi","family":"Men","sequence":"first","affiliation":[{"name":"Production Management and Engineering Research Centre, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera, 46022 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6487-3968","authenticated-orcid":false,"given":"Roberto","family":"Guidotti","sequence":"additional","affiliation":[{"name":"Guy Carpenter, New York, NY 10036, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6104-3079","authenticated-orcid":false,"given":"Javier A.","family":"Cuartas-Micieces","sequence":"additional","affiliation":[{"name":"Production Management and Engineering Research Centre, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera, 46022 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1392-1776","authenticated-orcid":false,"given":"Angel A.","family":"Juan","sequence":"additional","affiliation":[{"name":"Production Management and Engineering Research Centre, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera, 46022 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7250-5663","authenticated-orcid":false,"given":"Guillermo","family":"Franco","sequence":"additional","affiliation":[{"name":"Guy Carpenter, New York, NY 10036, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9352-9565","authenticated-orcid":false,"given":"Patricia","family":"Carracedo","sequence":"additional","affiliation":[{"name":"Production Management and Engineering Research Centre, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera, 46022 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8321-735X","authenticated-orcid":false,"given":"Laura","family":"Lemke-Verderame","sequence":"additional","affiliation":[{"name":"Guy Carpenter, New York, NY 10036, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Dilley, M. (2005). Natural Disaster Hotspots: A Global Risk Analysis, World Bank Publications.","DOI":"10.1596\/0-8213-5930-4"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"391","DOI":"10.37419\/LR.V6.I2.3","article-title":"Managing hurricane (and other natural disaster) risk","volume":"6","author":"Jerry","year":"2018","journal-title":"Tex. A M Law Rev."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Abtew, W. (2019). Hurricanes: Wind, rain, and storm surge. Extreme Hydrology and Climate Variability, Elsevier.","DOI":"10.1016\/B978-0-12-815998-9.00028-2"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Franco, G., Beer, M., Kougioumtzoglou, I., and Patelli, E. (2014). Earthquake mitigation strategies through insurance. Encyclopedia of Earthquake Engineering, Springer.","DOI":"10.1007\/978-3-642-36197-5_401-1"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"106477","DOI":"10.1016\/j.ocecoaman.2023.106477","article-title":"How does index-based insurance support marine disaster risk reduction in China? Evolution, challenges and policy responses","volume":"235","author":"Xue","year":"2023","journal-title":"Ocean. Coast. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1080\/10406026.2011.607066","article-title":"Parametric insurance: Using objective measures to address the impacts of natural disasters and climate change","volume":"23","author":"Nevius","year":"2011","journal-title":"Environ. Claims J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1111\/rmir.12146","article-title":"Application of parametric insurance in principle-compliant and innovative ways","volume":"23","author":"Lin","year":"2020","journal-title":"Risk Manag. Insur. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Franco, G., Lemke-Verderame, L., Guidotti, R., Yuan, Y., Bussi, G., Lohmann, D., and Bazzurro, P. (2024). Typology and design of parametric cat-in-a-box and cat-in-a-grid triggers for tropical cyclone risk transfer. Mathematics, 12.","DOI":"10.3390\/math12111768"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"527","DOI":"10.5194\/isprs-archives-XLII-3-527-2018","article-title":"On the influence of global warming on Atlantic hurricane frequency","volume":"42","author":"Hosseini","year":"2018","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"M\u00e9ndez-Tejeda, R., and Hern\u00e1ndez-Ayala, J.J. (2023). Links between climate change and hurricanes in the North Atlantic. PLoS Clim., 2.","DOI":"10.1371\/journal.pclm.0000186"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1038\/s41612-025-00919-y","article-title":"High prediction skill of decadal tropical cyclone variability in the North Atlantic and East Pacific in the met office decadal prediction system DePreSys4","volume":"8","author":"Monerie","year":"2025","journal-title":"npj Clim. Atmos. Sci."},{"key":"ref_12","first-page":"373","article-title":"Statistical and machine learning approaches for the minimization of trigger errors in parametric earthquake catastrophe bonds","volume":"41","author":"Calvet","year":"2017","journal-title":"SORT-Stat. Oper. Res. Trans."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101395","DOI":"10.1016\/j.cosust.2023.101395","article-title":"Climate catastrophe insurance for climate change: What do we know and what lies ahead?","volume":"66","author":"Nobanee","year":"2024","journal-title":"Curr. Opin. Environ. Sustain."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1193\/1.3479932","article-title":"Minimization of trigger error in cat-in-a-box parametric earthquake catastrophe bonds with an application to Costa Rica","volume":"26","author":"Franco","year":"2010","journal-title":"Earthq. Spectra"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1193\/030918EQS052M","article-title":"Parametric catastrophe bonds for tsunamis: CAT-in-a-Box trigger and intensity-based index trigger methods","volume":"35","author":"Goda","year":"2019","journal-title":"Earthq. Spectra"},{"key":"ref_16","first-page":"31","article-title":"Overcoming basis risk in parametric insurance","volume":"21","author":"Margan","year":"2021","journal-title":"Bimaquest"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1007\/s10669-023-09934-x","article-title":"A generalized framework for designing open-source natural hazard parametric insurance","volume":"43","author":"Steinmann","year":"2023","journal-title":"Environ. Syst. Decis."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Cummins, J.D., and Mahul, O. (2009). Catastrophe Risk Financing in Developing Countries: Principles for Public Intervention, World Bank Publications.","DOI":"10.1596\/978-0-8213-7736-9"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1057\/s41288-021-00220-y","article-title":"Bridging the gap between risk and uncertainty in insurance","volume":"46","author":"Zweifel","year":"2021","journal-title":"Geneva Pap. Risk Insur.-Issues Pract."},{"key":"ref_20","first-page":"24","article-title":"Money Matters: Rapid Post-Earthquake Financial Decision-Making","volume":"40","author":"Wald","year":"2016","journal-title":"Nat. Hazards Obs."},{"key":"ref_21","unstructured":"Wald, D.J., and Franco, G. (2017, January 9\u201313). Financial Decision-Making based on Near-Real-Time Earthquake Information. Proceedings of the 16th World Conference on Earthquake Engineering, Santiago de Chile, Chile."},{"key":"ref_22","first-page":"285","article-title":"Parametric insurance as an alternative to liability for compensating climate harms","volume":"12","author":"Horton","year":"2018","journal-title":"Carbon Clim. Law Rev."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Franco, G. (2013, January 16\u201320). Construction of customized payment tables for cat-in-a-box earthquake triggers as a basis risk reduction device. Proceedings of the International Conference on Structural Safety and Reliability (ICOSSAR), New York, NY, USA.","DOI":"10.1201\/b16387-793"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1193\/1.4000164","article-title":"Basis Risk of Earthquake Catastrophe Bond Trigger Using Scenario-Based versus Station Intensity\u2013Based Approaches: A Case Study for Southwestern British Columbia","volume":"29","author":"Goda","year":"2013","journal-title":"Earthq. Spectra"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1111\/mice.12093","article-title":"Seismic Risk Management of Insurance Portfolio Using Catastrophe Bonds","volume":"30","author":"Goda","year":"2015","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"105033","DOI":"10.1016\/j.cor.2020.105033","article-title":"A biased-randomized algorithm for optimizing efficiency in parametric earthquake (Re) insurance solutions","volume":"123","author":"Bayliss","year":"2020","journal-title":"Comput. Oper. Res."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Collich, G., Rosillo, R., Mart\u00ednez, J., Wald, D.J., and Durante, J.J. (2020). Financial risk innovation: Development of earthquake parametric triggers for contingent credit instruments. Natural Disasters and Climate Change: Innovative Solutions in Financial Risk Management, Springer International Publishing.","DOI":"10.1007\/978-3-030-43708-4_1"},{"key":"ref_28","first-page":"1","article-title":"Hurricane Bond Price Dependency on Underlying Hurricane Parameters","volume":"15","author":"Chang","year":"2020","journal-title":"Asia-Pac. J. Risk Insur."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3659","DOI":"10.1016\/j.eswa.2011.09.058","article-title":"Gradient boosting trees for auto insurance loss cost modeling and prediction","volume":"39","author":"Guelman","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Clemente, C., Guerreiro, G.R., and Bravo, J.M. (2025, December 01). Gradient Boosting in Motor Insurance Claim Frequency Modelling. Available online: https:\/\/aisel.aisnet.org\/capsi2023\/5\/.","DOI":"10.18803\/capsi.v23.53-69"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1080\/03461238.2024.2365390","article-title":"Enhanced gradient boosting for zero-inflated insurance claims and comparative analysis of CatBoost, XGBoost, and LightGBM","volume":"2024","author":"So","year":"2024","journal-title":"Scand. Actuar. J."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chevalier, D., and C\u00f4t\u00e9, M.P. (2024). From Point to probabilistic gradient boosting for claim frequency and severity prediction. arXiv.","DOI":"10.1007\/s13385-025-00428-5"},{"key":"ref_33","unstructured":"Nordhaus, W.D. (2025, December 01). The Economics of Hurricanes in the United States. Available online: https:\/\/www.nber.org\/papers\/w12813."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Branco, P., and Torgo, L. (2019, January 5\u20138). A study on the impact of data characteristics in imbalanced regression tasks. Proceedings of the 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Washington, DC, USA.","DOI":"10.1109\/DSAA.2019.00034"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1007\/s10462-024-10724-3","article-title":"Resampling strategies for imbalanced regression: A survey and empirical analysis","volume":"57","author":"Avelino","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Branco, P., Torgo, L., and Ribeiro, R.P. (2017, January 5\u20138). Exploring resampling with neighborhood bias on imbalanced regression problems. Proceedings of the Progress in Artificial Intelligence: 18th EPIA Conference on Artificial Intelligence, EPIA 2017, Porto, Portugal. Proceedings 18.","DOI":"10.1007\/978-3-319-65340-2_42"},{"key":"ref_37","unstructured":"Wu, W., Kunz, N., and Branco, P. (2020, January 19\u201323). Imbalancedlearningregression-a python package to tackle the imbalanced regression problem. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Grenoble, France."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.neucom.2018.11.100","article-title":"Pre-processing approaches for imbalanced distributions in regression","volume":"343","author":"Branco","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_39","unstructured":"Branco, P., Torgo, L., and Ribeiro, R.P. (2017, January 22). SMOGN: A pre-processing approach for imbalanced regression. Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications, Skopje, Macedonia."},{"key":"ref_40","unstructured":"Torgo, L., and Ribeiro, R. (2003, January 22\u201326). Predicting outliers. Proceedings of the European Conference on Principles of Data Mining and Knowledge Discovery, Cavtat\/Dubrovnik, Croatia."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2187","DOI":"10.1007\/s10994-021-06023-5","article-title":"Density-based weighting for imbalanced regression","volume":"110","author":"Steininger","year":"2021","journal-title":"Mach. Learn."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1111\/exsy.12081","article-title":"Resampling strategies for regression","volume":"32","author":"Torgo","year":"2015","journal-title":"Expert Syst."},{"key":"ref_43","unstructured":"Kubat, M., and Matwin, S. (1997, January 8\u201312). Addressing the curse of imbalanced training sets: One-sided selection. Proceedings of the Icml. Citeseer, Nashville, TN, USA."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Kamalov, F., Leung, H.H., and Cherukuri, A.K. (2023, January 20\u201323). Keep it simple: Random oversampling for imbalanced data. Proceedings of the 2023 Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates.","DOI":"10.1109\/ASET56582.2023.10180891"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/1007730.1007735","article-title":"A study of the behavior of several methods for balancing machine learning training data","volume":"6","author":"Batista","year":"2004","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"497","DOI":"10.19139\/soic.v6i4.479","article-title":"Weighted machine learning","volume":"6","author":"Hashemi","year":"2018","journal-title":"Stat. Optim. Inf. Comput."},{"key":"ref_47","unstructured":"Taylor, G., Menon, S., Ru, H., Wright, R., Hunt, X., and Abbey, R. (April, January 29). Interpretation methods for black-box machine learning models in insurance rating-type applications. Proceedings of the SAS Global Forum, Washington, DC, USA."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1080\/03461238.2022.2081816","article-title":"LocalGLMnet: Interpretable deep learning for tabular data","volume":"2023","author":"Richman","year":"2023","journal-title":"Scand. Actuar. J."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"ref_50","unstructured":"Men, Y., Guidotti, R., Cuartas-Micieces, J.A., Juan, A.A., Franco, G., Carracedo, P., and Lemke-Verderame, L. (2025). [Synthetic Dataset] a Hybrid Machine Learning Framework for Highly Imbalanced Data Predicting Hurricane Losses (Version 1), ResearchGate."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/15\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T11:02:28Z","timestamp":1766487748000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,23]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["a19010015"],"URL":"https:\/\/doi.org\/10.3390\/a19010015","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,23]]}}}