Forecasting Risks of the Transport Insurance Market in Russia Using Machine Learning

The purpose of the study is to develop and apply a model for predicting potential losses under a CTP policy using machine learning techniques. The relevance of the topic is due to the importance of the role played by the insurance market, and, in particular, transport insurance in the development of the Russian economy. This relevance is supported by the high loss ratio for this type of insurance, as well as the need to optimize market conditions. The object of this research is the Russian insurance sector. The subject of the study is machine learning techniques that allow predicting CTP losses based on input parameters characterizing data about the insured and their vehicle. The paper compares the effectiveness of ensemble machine learning methods with the traditional generalized linear method of predicting compulsory motor insurance losses. The study divides CTP losses into traditional and direct categories. It has been shown that the effectiveness of applying boosting machine learning models for forecasting is higher than using Random Forest and GLM. Factors that significantly affect the frequency and severity of insured events include: the number of minor accidents on a vehicle, the number of drivers, and the CBM coefficient. Other factors include the minimum length of service for a driver in a policy, the power of a vehicle, and the type of location where the vehicle is used. It has been concluded that the growth of the projected loss is positively influenced by the number of accidents, the number of drivers in the policy, low seniority and low age of drivers. The influence of the gender composition of drivers is highlighted: an increase in the number of female drivers leads to a decrease in insurance risks under the CTP policy.

1. Shcherbanin Yu.A. Transport and economic growth: Interconnection and impact. Evraziiskaya ekonomicheskaya integratsiya = Journal of Eurasian Economic Integration. 2011;(3):65-78. (In Russ.).

2. Nizhegorodtsev R.M., Gorid’ko N.P., Roslyakova N.A. The relationship between the volume of GRP and the development of transport infrastructure: The experience of clustering regions of Russia. Regional’naya ekonomika: teoriya i praktika = Regional Economics: Theory and Practice. 2013;(33):19-24. (In Russ.).

3. Vasil’eva T.S. Current issues of regional insurance market development and its role in the economy. Problemy razvitiya territorii = Problems of Territory’s Development. 2020;(3):103-115. (In Russ.). DOI: 10.15838/ptd.2020.3.107.7

4. Prokop’eva E.L. The modern Russian insurance market: Problems and potential for development. Finansy i kredit =Finance and Credit. 2019;25(1):177-195. (In Russ.). DOI: 10.24891/fc.25.1.177

5. Rybakov S.I. The assessment of the economic efficiency of transport insurance in the Russian Federation. ETAP: ekonomicheskaya teoriya, analiz, praktika = ETAP: Economic Theory, Analysis, and Practice. 2022;(4):135-167. (In Russ.). DOI: 10.24412/2071-6435-2022-4-135-167

6. Shanikhina N.N., Okuneva A.A. Problems and prospects of development of auto insurance in Russia. International Journal of Advanced Studies. 2018;8(1):169-179. (In Russ.). DOI: 10.12731/2227-930X-2018-1-169-179

7. Komarova N.V. The mainstream of the modern Russian insurance market development. Vestnik SanktPeterburgskogo universiteta. Ekonomika = St. Petersburg University Journal of Economic Studies. 2013;(1):91-99. (In Russ.).

8. Tulenty D.S. Efficiency of auto insurance in the Russian Federation. Imushchestvennye otnosheniya v Rossiiskoi Federatsii = Property Relations in the Russian Federation. 2022;(9):54-65. (In Russ.). DOI: 10.24412/2072-4098-2022-9252-54-65

9. Tsyganov A.A., Bryzgalov D.V. Digitalization of the insurance market: Tasks, problems and prospects. Ekonomika. Nalogi. Pravo = Economics, Taxes & Law. 2018;11(2):111-120. (In Russ.). DOI: 10.26794/1999-849X-2018-11-2-111-120

10. Sharapova S.A. Conceptual issues of functioning and problems of development of vertically integrated marketing insurance systems. Vestnik MGPU. Seriya: Ekonomika = MCU Journal of Economic Studies. 2018;(2):43-53. (In Russ.).

11. Kotlobovskii I.B., Sagan A.I. State regulation of the Russian insurance market in the context of accession to the WTO. Finansy = Finance. 2012;(12): 47-53. (In Russ.).

12. Beketnova Yu.M. Comparative analysis of machine learning methods to identify signs of suspicious transactions of credit institutions and their clients. Finance: Theory and Practice. 2021;25(5):186-199. DOI: 10.26794/2587-5671-2020-25-5-186-199

13. Abdelhadi S., Elbahnasy K., Abdelsalam M. A proposed model to predict auto insurance claims using machine learning techniques. Journal of Theoretical and Applied Information Technology. 2020;98(22):3428-3437.

14. Hsu Y.-C., Chou P.-L., Shiu Y.-M. An examination of the relationship between vehicle insurance purchase and the frequency of accidents. Asia Pacific Management Review. 2016;21(4):231-238. DOI: 10.1016/j.apmrv.2016.08.001

15. Yarkova O.N., Fedorova P.S. Mathematical modeling of financial indicators of an insurance company under motor insurance contracts. In: Udalov F.E., Bondarenko V.V., eds. Increasing the managerial, economic, social and innovative-technical potential of enterprises, industries and national economic complexes. Proc. 13th Int. sci.-pract. conf. (Penza, May 19-20, 2022). Penza: Penza State Agrarian University; 2022:334-337. (In Russ.).

16. Makarenko E. A. Modeling tools to predict the bankruptcy of insurance companies. Izvestiya vysshikh uchebnykh zavedenii. Seriya: Ekonomika, finansy i upravlenie proizvodstvom = News of Higher Educational Institutions. Series: Economy, Finance and Production Management. 2021;(2):43-50. (In Russ.). DOI: 10.6060/ivecofin.2021482.533

17. Tsyganov A. A. Yazykov A. D., Yanenko E. A., Gryzenkova Yu.V. Interpreting the change of the age and experience coefficient in Motor Third-Party Liability Insurance. Finance: Theory and Practice. 2020;24(4):31- 46. DOI: 10.26794/2587-5671-2020-24-4-31-46

18. Kharlamov A.V. Forecasting models in insurance. In: Transforming the insurance industry for sustainable development in the new environment. Proc. 22nd Int. sci.-pract. conf. (Moscow, June 2–3, 2021). Moscow: AllRussian Union of Insurers; 2021:231-236. (In Russ.).

19. Yeo A.C., Smith K.A., Willis R.J., Brooks M. Clustering technique for risk classification and prediction of claim costs in the automobile insurance industry. Intelligent Systems in Accounting, Finance and Management. 2001;10(1):39-50. DOI: 10.1002/isaf.196

20. Babii A., Ghysels E., Striaukas J. Machine learning time series regressions with an application to nowcasting. Journal of Business & Economic Statistics. 2022;40(3):1094-1106. DOI: 10.1080/07350015.2021.1899933

21. Ball R.T., Ghysels E. Automated earnings forecasts: Beat analysts or combine and conquer? Management Science. 2018;64 (10):4936-4952. DOI: 10.1287/mnsc.2017.2864

22. Hanafy M., Ming R. Machine learning approaches for auto insurance Big Data. Risks. 2021;9(2):42. DOI: 10.3390/risks9020042

23. Zanke P., Sontakke D. Leveraging machine learning algorithms for risk assessment in auto insurance. Journal of Artificial Intelligence Research. 2021;1(1):21-39.

24. Breiman L. Random forests. Machine learning. 2001;45(1):5-32. DOI: 10.1023/A:1010933404324

25. Prokhorenkova L., Gusev G., Vorobev A., Dorogush A. V., Gulin A. CatBoost: Unbiased boosting with categorical features. In: Bengio S., et al., eds. Proc. 32nd Conf. on neural information processing systems (NeurIPS 2018). (Montreal, December 3-8, 2018). San Diego, CA: Neural Information Processing Systems Foundation; 2018:75-90. (Advances in neural information processing systems. Vol. 31).

26. Dorogush A.V., Ershov V., Gulin A. CatBoost: Gradient boosting with categorical features support. arXiv preprint. 2018. DOI: 10.48550/arXiv.1810.11363