The Assessment of Early Warning for Insurance Company Using Machine Learning Methods

Year 2025, Early View, 1 - 1

Günay Burak Koçer , Sevtap Selcuk-kestel

https://doi.org/10.35378/gujs.1365256

Abstract

Developing an early warning indicator is essential to strengthen the financial structure and take necessary precautions in a non-life insurance company. This paper aims to implement machine learning techniques on financial ratios to estimate the capital requirement ratio and investigate the solvency of an insurance company. For this purpose, the historical ratios of insurance companies in an emerging market are considered in accordance with the regulator’s solvency requirements. The ratios collected based on the performances of insurance companies in Türkiye are studied in two cases based on the number of features to be included in to four machine learning algorithms. “Full” data set with 69 and “Boruta” implemented data set with 33 ratios are employed to depict the efficiency of methods in predicting the early warning state of the company in terms of their capital requirement ratio predictions. Additionally, the assessment of these predictions to be utilized as an early warning indicator is performed. The findings illustrate that proposed early warning model predicts well the capital requirement ratio one year in advance. Moreover, among four ML methods, XGBoost achieves a prediction accuracy of 85% for estimating the state of the solvency in an insurance company compared to the other algorithms.

Keywords

Capital requirement ratio, Early warning, Solvency, Machine learning, Financial ratios

References

• [1] Alessi, L., Antunes, A., Babeckk, J., Baltussen, S., Behn, M., Bonfim, D., Bush, O., Detken, C., Frost, J., Guimaraes, R., Havranek, T., Joy, M., Kauko, K., Mateju, J., Monteiro, N., Neudorfer, B., Peltonen, T. A., Rusnak, M., Rodrigues, P. M. M., Schudel, W., Sigmund, M., Stremmel, H., Smidkova, K., van Tilburg, R., Vasicek, B. and Zigraiova, D., “Comparing different early warning systems: results from a horse race competition among members of the macro-prudential research network”, European Central Bank, (2015).
• [2] Sahajwala, R., and Van den Bergh, P., “Supervisory Risk Assessment And Early Warning Systems”, Basel Committee on Banking Supervision, (2000).
• [3] Wong, J., “A comparison of solvency requirements and early warning systems for life insurance companies in china with representative world practices”, North American Actuarial Journal, 6(1): 91-112, (2002).
• [4] Brockett, P.L., Cooper, W. W., Golden, L. L. and Pitaktong, U., “A neural network method for obtaining an early warning of insurer insolvency”, The Journal of Risk and Insurance, 61(3): 402-424, (1994).
• [5] Genc, A., “Measuring Financial Adequacy for Non-life Insurance Companies and Early Warning Model Recommendation for Turkey”, Phd.Thesis, Ankara University Institute of Social Sciences, Ankara, (2002).
• [6] Davis, E.P., and Karim, D., “Comparing early warning systems for banking crises”, Journal of Financial Stability, 4(2): 89-120, (2008).
• [7] Isseveroglu, G., and Gucenme, U., “Early warning model with statistical analysis procedures in Turkish insurance companies”, African Journal of Business Management, 4(5): 623-630, (2010).
• [8] Ito, Y., Kitamura, T., Nakamura, K., and Nakazawa, T., “New Financial Activity Indexes: Early Warning System For Financial Imbalances In Japan”, Bank of Japan, (2014).
• [9] Tornoa, E.T., and Tiub, T.S., “An early warning system on the propensity of survival and failure of non-life insurance firms in the Philippines”, Journal of Business and Finance, 2(1): 47-55, (2014).
• [10] Ocak, G., “An Early Warning Model for Turkish Insurance Companies”, MSc. Thesis, Middle East Technical University Institute of Applied Mathematics, Ankara, (2015).
• [11] Danieli, L., and Jakubik, P., “Early warning system for the European insurance sector”, EIOPA, Risks and Financial Stability Department, (2018).
• [12] Du, M., Liu, B., and Zhou, H., “Construction of financial early warning model based on machine learning technology”, International Conference on Multi-modal Information Analytics, 136: 75-83, (2022).
• [13] Beaver, W.H., “Financial ratios as predictors of failure”, Journal of Accounting Research, 4(1): 71-111, (1966).
• [14] Altman, E.I., “Financial ratios, discriminant analysis and the prediction of corporate bankruptcy”, The Journal of Finance, 23(4): 589-609, (1968).
• [15] Deakin, E.B., “A discriminant analysis of predictors of business failure”, Journal of Accounting Research, 10(1): 167-179, (1972).
• [16] Libby, R., “Accounting ratios and the prediction of failure: some behavioral evidence”, Journal of Accounting Research, 13(1): 150-161, (1975).
• [17] Meyer, P.A., and Pifer, H.W., “Prediction of bank failures”, The Journal of Finance, 25(4): 853-868, (1970).
• [18] Edmister, R.O., “An empirical test of financial ratio analysis for small business failure prediction”, The Journal of Financial and Quantitative Analysis, 7(2): 1477-1493, (1972).
• [19] Blum, M., “Failing company discriminant analysis”, Journal of Accounting Research, 12(1): 1-25, (1974).
• [20] Truong, C., Sheen, J., Trück, S. and Villafuerte, J., “Early warning systems using dynamic factor models: An application to Asian economies”, Journal of Financial Stability, 58: 100885, (2022).
• [21] Tanaka, K., Kinkyo, T., and Hamori, S., “Random forests-based early warning system for bank failures”, Economics Letters, 148: 118-121, (2016).
• [22] Alessi, L., and Detken, C., “Identifying excessive credit growth and leverage”, Journal of Financial Stability, 35: 215-225, (2018).
• [23] Holopainen, M., and Sarlin, P., “Toward robust early-warning models: a horse race, ensembles and model uncertainty”, Quantitative Finance, 17(12): 1933-1963, (2017).
• [24] Yan, C., Wang, L., Liu, W., and Qi, M., “Financial early warning of non-life insurance company based on RBF neural network optimized by genetic algorithm”, Concurrency and Computation: Practice and Experience, 30(23): e4343, (2018).
• [25] Lowe, J., and Pryor, L., “Neural Networks v. GLMs in pricing general insurance”, General Insurance Convention, Workshop, (1996).
• [26] Guelman, L., “Gradient boosting trees for auto insurance loss cost modeling and prediction”, Expert Systems with Applications, 39(3): 3659-3667, (2012).
• [27] Spedicato, G.A., Dutang, C., and Petrini, L., “Machine learning methods to perform pricing optimization. A comparison with standard GLMs.”, Variance, 12(1): 69-89, (2018).
• [28] Bruns, W., Introduction to financial ratios and financial statement analysis, President and Fellows of Harvard College, (1992).
• [29] Rebala, G., Ravi, A., and Churiwala, S., An introduction to machine learning. Springer, (2019).
• [30] Martin, T.M., Harten, P., Young, D. M., Muratov, E. N., Golbraikh, A., Zhu, H. and Tropsha, A., “Does rational selection of training and test sets improve the outcome of QSAR modeling?”, Journal of Chemical Information and Modeling, 52(10): 2570-8, (2012).
• [31] Kursa, M.B., “Boruta for those in a hurry”, 1-6, (2020).
• [32] Kursa, M.B., and Rudnicki, W.R., “Feature selection with theBorutaPackage”, Journal of Statistical Software, 36(11): 1-13, (2010).
• [33] Stoppiglia, H., Dreyfus, G., Dubois, R. and Oussar, Y., “Ranking a random feature for variable and feature selection”, Journal of Machine Learning Research, 3(Mar): 1399-1414, (2003).
• [34] Henckaerts, R., Côté, M., Antonio, K., and Verbelen, R., “Boosting Insights in Insurance Tariff Plans with Tree-Based Machine Learning Methods”, North American Actuarial Journal, 25(2): 255-285, (2020).
• [35] Cook, D., Practical Machine Learning with h2o - Powerful, Scalable Techniques for Deep Learning and AI, O'Reilly Media, Inc., (2016).
• [36] Candel, A., Parmar, V., LeDell, E., and Arora, A., “Deep Learning with H2O. 5th ed.”, H2O.ai Inc., (2016).
• [37] Malohlava, M., and Candel, A., “Gradient Boosting Machine with H2O. 7th ed.”, H2O.ai Inc., (2018).
• [38] Chen, T., He, T., Benesty, M., Khotilovich, V. and Tang, Y., Xgboost: eXtreme Gradient Boosting. R package version 0.4-2, 1-4, (2015).
• [39] Chen, T., and Guestrin, C., XGBoost: A Scalable Tree Boosting System, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, 785-794, (2016).
• [40] Koçer, G.B., “Early Warning Model with Machine Learning for Turkish Insurance Sector”, MSc. Thesis, Middle East Technical University Institute of Applied Mathematics, Ankara, (2019).
• [41] Insurance Association of Türkiye, “Financial and technical statements by company”, https://www.tsb.org.tr/tr/istatistik/finansal-tablolar/sirket-bazinda-mali-ve-teknik-tablolar, Access date: 25.09.2024.
• [42] Ministry of Treasury and Finance of the Republic of Türkiye, “Regulation on Measurement and Assessment of Capital Requirements of Insurance and Reinsurance Companies and Pension Companies”, The Official Gazette of the Turkish Republic, 29454, Türkiye, (2015).