A MLP Neural Network Approach for Validation of Health Insurance Customers in Big Data Environments

Subject Areas : Intelligent Multimedia Processing and Communication Systems (IMPCS)

Saeed Shouri ¹ (PhD. Student, Ferdowsi University of Mashhad, Mashhad, Iran)
ali cheshomi ² (Assistant Professor, Ferdowsi University of Mashhad, Mashhad, Iran)
Ahmad Seifi ³ (Associate Professor of Economics, Department of Economics, Faculty of Economics and Administrative Sciences, Ferdowsi University of Mashhad)
Rasoul Ramezani ⁴ ( Assistant Professor,The University of Texas at Dallas, Dallas, US)
Taghi Ebrahimi Salari ⁵ (Associate Professor, Ferdowsi University of Mashhad, Mashhad, Iran)

Received: 2024-04-16 Accepted : 2024-06-08 Published : 2024-06-21

Keywords: Validation, health insurance, Claims-Based Risk, MLP neural network,

Abstract :

Introduction: Inadequate risk assessment of policyholders is a significant challenge in the health insurance industry. This research proposes a customer validation model for health insurance plans, focusing specifically on employees of the East Iran Oil Company.

Method: In this study, a Multi-Layer Perceptron (MLP) neural network with six steps is employed for customer validation. Weight training, a crucial step in neural network implementation, determines the influence of explanatory variables on the model's output. The trained model is then used for validation.

Results: Validation results indicate that health insurance claim variables and specific disease variables have the highest impact on unhealthy customer classification. Notably, the validation process identified approximately 1.8% of the population as "unhealthy." This seemingly small group accounts for a disproportionately high 17.47% of the company's total health insurance claims, despite currently being classified and charged premiums as healthy individuals.

Discussion: The proposed validation model offers a practical approach for insurance companies to assess customer risk profiles and tailor premiums accordingly. This approach promotes a more equitable and sustainable insurance system. JEL classification: C52, I13, C45

References:

[1] European, G. C. A. (2011). Use of age and disability as rating factors in insurance: why are they used and what would be th implications of restricting their use?, position paper.
[2] Feldman, R. (2001). An economic explanation for fraud and abuse in public medical care programs. The Journal of Legal Studies, 30(S2), 569-577.
[3] Behrendt, C. A., Schwaneberg, T., Hischke, S., Müller, T., Petersen, T., Marschall, U., ... & Kriston, L. (2020). Data privacy compliant validation of health insurance claims data: the IDOMENEO approach. Das Gesundheitswesen, 82(S 02), S94-S100.
[4] Lee, G., Kim, W., Oh, H., Youn, B. D., & Kim, N. H. (2019). Review of statistical model calibration and validation—from the perspective of uncertainty structures. Structural andMultidisciplinary Optimization, 60, 1619-1644.
[5] Huber, L. (2023). Validation of computerized analytical systems. CRC Press.
[6] Dionne, G., & Rothschild, C. (2014). Risk classification and health insurance. Encyclopedia of Health Economics, 3, 272-280.
[7] Mariner, wendy k. (2013). The affordable care act and Health promotion: The role of insurance in defining of responsibility for health risks and costs, Boston University school of law public law and Legal Research paper no, pp:10-13.
[8] Hadian, M., Ghaderi, H., & Moeini, M. (2007). Estimating Demand Function for Supplementary Health Insurance Case Study: Iran Insurance Corporation.
[9] DAGHIGHI, A. A. R., FAGHIH, N. M., & AGHASSI, K. S. (2010). Estimating Demand Function of Supplementary Health Insurance in Iranian Insurance Industry.
[10] Abbasi, E., Taghiabadi, M. (2011). The effect of economic factors on the demand for supplementary medical insurance. Insurance Journal, 104(26), 57-80.
[11] Nakhaei Aghimuni, M., & Kamuei, M. (2010). Estimating demand function of private insurance in urban states of Iran: Tobit analysis. Insurance Industry, 25(3), 3-28.
[12] Ebrahimzadeh, J., Mohammad, A. R. A. B., & Emamgholipour, S. (2015). Determinants of supplementary health insurance demand: case study of Iran. Iranian journal of public health, 44(11), 1563-1565.
[13] Nosratnejad, S. H., Purreza, A., Moieni, M., & Heydari, H. (2014). Factors affecting the demand for private health insurance in Tehran. Hospital, 13(2), 37-44.
[14] Vafaee Najar, A., Karimi, I. R. A. J., & Seydnowzadi, M. (2007). A comparative study between complementary health assurance structure and content in selected countries and presenting a paradigm for Iran. Journal of Health Administration, 10(28), 57-64.
[15] Gol-Alizadeh, E., Pirouzian, A., & Jabbari, M. R. (2018). Improving supplemental health insurance in Iran and how to achieve it. Iran J Health Insur, 1(1), 2-12.
[16] Mohebi, T. (2018). Critique of health insurance configuration in developing countries. Iranian Journal of Health Insurance, 1(1-2), 1-2.
[17] Riahifar, M., 2015. Designing a risk management model for medical insurance for Iran. Insurance industry quarterly, year 21, number 4, 119-155.
[18] Choudhry, N. K. (2017). Randomized, controlled trials in health insurance systems. New England Journal of Medicine, 377(10), 957-964.
[19] Olivieri, A., & Pitacco, E. (2015). Introduction to insurance mathematics: technical and financial features of risk transfers. Springer.
[20] Ritacco, E. (2014). Health insurance. Basic Actuarial Models, Cham, Switzerland: Springer Verlag.
[21] Lima Ramos, P. (2017). Premium calculation in insurance activity. Journal of Statistics and Management Systems, 20(1), 39-65.
[22] Boucher, J. P., & Inoussa, R. (2014). A posteriori ratemaking with panel data. ASTIN Bulletin: The Journal of the IAA, 44(3), 587-612.
[23] Koh, H. C., & Tan, G. (2011). Data mining applications in healthcare. Journal of healthcare information management, 19(2), 65.
[24] Rizal, A., & Hartati, S. (2016). Recurrent neural network with Extended Kalman Filter for prediction of the number of tourist arrival in Lombok. In Proceedings of the International Conference on Informatics and Computing (ICIC). Academic Press; . doi:10.1109/IAC.2016.7905712.
[25] Manry, M. T., Chandrasekaran, H., & Hsieh, C. H. (2018). Signal processing using the multilayer perceptron. In Handbook of Neural Network Signal Processing (pp. 2-1). CRC Press.
[26] Delashmit, W. H., & Manry, M. T. (2005, May). Recent developments in multilayer perceptron neural networks. In Proceedings of the seventh annual memphis area engineering and science conference, MAESC (Vol. 7, p. 33).
[27] Yang, Z. R., Platt, M. B., & Platt, H. D. (1999). Probabilistic neural networks in bankruptcy prediction. Journal of business research, 44(2), 67-74.
[28] Jaworeck, S. (2022). A New Approach for Constructing a Health Care Index including the Subjective Level. International Journal of Environmental Research and Public Health, 19(15), 9686.
[29] Vujović, Ž. (2021). Classification model evaluation metrics. International Journal of Advanced Computer Science and Applications, 12(6), 599-606.
[30] Powers, D. M. (2020). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061.