Bridging Master Data Governance and Weather Intelligence for Proactive Insurance Claims Prediction
DOI:
https://doi.org/10.63282/3050-9416.IJAIBDCMS-V7I1P140Keywords:
Weather Intelligence, Insurance Claim Prediction, Disaster Risk Modeling, Random Forest, Extreme Weather Events, Machine LearningAbstract
Extreme weather events are increasingly contributing to significant property damage and insurance losses, necessitating the development of predictive frameworks that integrate environmental intelligence with disaster data. This paper proposes a Weather-Governed Insurance Claim Prediction Framework (WGICPF) to forecast the likelihood of insurance claims resulting from extreme weather events. The framework utilizes disaster event records (783 events) and district-level rainfall observations, integrated through a structured data governance pipeline to ensure data quality and consistency. Weather intelligence features, including rainfall intensity and anomaly, are combined with disaster attributes to construct a comprehensive risk feature space. A Random Forest classifier is employed to predict the probability of insurance claim occurrence, where disaster damage indicators are used as proxies for insurance claims. Experimental results demonstrate strong predictive performance, achieving an accuracy of 80.4%, precision of 0.84, recall of 0.79, and an F1-score of 0.81, outperforming baseline logistic regression and weather-only models. Furthermore, the framework is validated using a USA-based disaster dataset (SHELDUS), demonstrating consistent performance across different geographic contexts. These findings highlight the effectiveness and scalability of integrating weather intelligence with disaster data for proactive insurance risk prediction.
References
1. Abdi MJ, Raffar N, Zulkafli Z, Nurulhuda K, Rehan BM, Muharam FM, ..., Tangang F (2021). Index-based insurance and hydroclimatic risk management in agriculture: a systematic review of index selection and yield-index modelling methods. Int J Disaster Risk Reduct, 67. DOI: 10.1016/j.ijdrr.2021.102653
2. Abdul LA, Biekpe N (2016). Determinants of life insurance consumption in Africa. Res Int Bus Financ, 37, 17–27. DOI: 10.1016/j.ribaf.2015.10.016
3. Abrego-Pérez AL, Boonman TM, Valencia-Arboleda CF (2025). Index insurance for simultaneous flooding and drought risks with insufficient data: a two-step approach. Stoch Environ Res Risk Assess, 39, 2769–2788. DOI: 10.1007/s00477-025-02966-6
4. Akhter W, Pappas V, Khan SU (2017). A comparison of Islamic and conventional insurance demand: worldwide evidence during the global financial crisis. Res Int Bus Financ, 42, 1401–1412. DOI: 10.1016/j.ribaf.2017.07.079
5. Ankan A, Textor J (2024). pgmpy: a Python toolkit for Bayesian networks. J Mach Learn Res, 25(265), 1–8.
6. Baltagi BH (2021). Econometric analysis of panel data, 6th edn. Springer Cham. DOI: 10.1007/978-3-030-53953-5
7. Barnett BJ, Mahul O (2007). Weather index insurance for agriculture and rural areas in lower-income countries. Am J Agric Econ, 89(5), 1241–1247. DOI: 10.1111/j.1467-8276.2007.01091.x
8. Barons MJ, Walsh LE, Salakpi EE, Nichols L (2024). A decision support system for sustainable agriculture and food loss reduction under uncertain agricultural policy frameworks. Agriculture, 14(3), 458. DOI: 10.3390/agriculture14030458
9. Bashari H, Smith C, Bosch OJH (2009). Developing decision support tools for rangeland management using Bayesian belief networks. Rangel J, 31(3), 311–318. DOI: 10.1071/RJ09001
10. Beck HE, van Dijk AIJM, Levizzani V, Schellekens J, Miralles DG, Martens B, de Roo A (2017). MSWEP: 3-hourly 0.25° global gridded precipitation (1979–2015) by merging gauge, satellite, and reanalysis data. Earth Syst Sci Data, 9(2), 913–935. DOI: 10.5194/hess-21-589-2017
11. Bedoya-Soto JM, Acevedo E, Sauchyn D, Poveda G, Urán A (2025). El Niño-Southern Oscillation impacts in a coffee-growing region of Colombia and adaptation mechanisms among coffee producers. J Environ Stud Sci. DOI: 10.1007/s13412-025-01038-z
12. Bokusheva R (2014). Improving the effectiveness of weather-based insurance: an application of copula approach. MPRA Paper No. 62339. University Library of Munich. Retrieved March 12, 2025, from MPRA
13. Bokusheva R (2018). Using copulas for rating weather index insurance contracts. J Appl Stat, 45(13), 2328–2356. DOI: 10.1080/02664763.2017.1420146
14. Blue Marble (2022). Café Seguro. Protegemos a Nuestros Caficultores. Blue Marble Microinsurance and Seguro Bolivar. Retrieved January 27, 2025, from: Seguros Bolivar
15. Breiman L (2001). Random forests. Mach Learn, 45(1), 5–32. DOI: 10.1023/A:1010933404324
16. Carter MR, de Janvry A, Sadoulet E, Sarris A (2017). Index insurance for developing country agriculture: a reassessment. Annu Rev Resour Econ, 9(1), 421–438. DOI: 10.1146/annurev-resource-100516-053352
17. Cepal (2023). Economic Survey of Latin America and the Caribbean: Financing a sustainable transition: investment for growth and climate change action. NU:CEPAL. Retrieved January 21, 2025, from: CEPAL Repository
18. Clarke DJ (2016). A theory of rational demand for index insurance. Am Econ Journal: Microeconomics, 8(1), 283–306. DOI: 10.1257/mic.20140103
19. Collier B, Skees J (2012). Increasing the resilience of financial intermediaries through portfolio-level insurance against natural disasters. Nat Hazards, 64(1), 55–72.
20. Coughlan de Perez E, Choularton R, van den Homberg M, Suarez P (2023). Anticipatory index-based insurance for drought risk: lessons from African Risk Capacity. SSRN. DOI: 10.2139/ssrn.4976185
21. Dávila F, Alcaraz C, Hernández J (2024). Modeling wheat yield and GHG trade-offs using Bayesian networks under climate uncertainty. Front Artif Intell, 7, Article 1402098. DOI: 10.3389/frai.2024.1402098
22. Dormann CF, Elith J, Bacher S, Buchmann C, Carl G, Carré G, Marquéz JRG, Gruber B, Lafourcade B, Leitão PJ, Münkemüller T, McClean C, Osborne PE, Reineking B, Schröder B, Skidmore AK, Zurell D, Lautenbach S (2013). Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography, 36(1), 27–46. DOI: 10.1111/j.1600-0587.2012.07348.x
23. Erec H, Finger R, Musshoff O (2012). Hedging weather risk on aggregated and individual farm-level. Agricultural Finance Review, 72(3), 471–487. Available from: ResearchGate
24. FAO (2021). The State of Food and Agriculture: Making agrifood systems more resilient to shocks and stresses. Food and Agriculture Organization. Retrieved January 21, 2025, from: FAO Knowledge
25. Federación Nacional de Cafeteros de Colombia (FNCC) (2024). Colombia proyecta producción de café superior a los 13 millones de sacos en 2024. Reuters. Retrieved May 11, 2025, from: Reuters
26. Figueiredo R, Martina ML, Stephenson DB, Youngman BD (2018). A probabilistic paradigm for the parametric insurance of natural hazards. Risk Anal, 38(11), 2400–2414. DOI: 10.1111/risa.13122
27. Gall, M., Borden, K. A., & Cutter, S. L. (2009). When do losses count? Six fallacies of natural hazards loss data. Bulletin of the American Meteorological Society, 90(6), 799–810.SHELDUS Database (Version 24.0). Arizona State University. Retrieved from https://cemhs.asu.edu/sheldus
