Subject. The Russian automotive market, which has undergone a structural transformation after 2022. Objectives. Development and testing of a predictive machine learning model (binary logistic regression) to assess the probability of a successful entry of a new car model into the Russian market based on its technical and operational characteristics (using the example of Haval Xialong Max). Methods. The research is based on econometric modeling: the construction and evaluation of a binary logistic regression model based on a representative sample of 70 models sold in 2024 using Python libraries (Statsmodels, Pandas). ROC analysis and metrics Accuracy, Precision, Recall, and F1-score were used to evaluate the model. Results. The evaluation of the model showed high predictive quality (Accuracy = 85%, AUC = 0.94). It has been established that the maximum speed and average cost of a car are the most statistically significant factors of demand. Based on the model, the probability of high sales of the new Haval Xialong Max model is 79%. A targeted marketing strategy has been developed for this model. Conclusions. After 2022, the Russian car market has radically transformed with the dominance of Chinese brands. The created logistic regression model is an effective analytical tool for predicting the success of new models, demonstrating high accuracy. The model confirmed the high potential of the Haval Xialong Max crossover in the Russian market. The research results have practical value for manufacturers and dealers in making informed decisions about entering the market and developing marketing strategies.
Sokolova E.S. [Assessing the effectiveness of the russian transport system: analysis of dynamics and development prospects]. Regionologiya, 2025, no. 4, pp. 697–714. (In Russ.) DOI: 10.15507/2413-1407.129.033.202504.697-714 EDN: ITLMUR
Strubalin P.V. [Transformation of the Russian car market]. Ekonomicheskie nauki, 2024, T. 3, no. 232, pp. 362–366. (In Russ.) DOI: 10.14451/1.232.362 EDN: MIYRGN
Kel'chevskaya N.R., Kontoboitseva A.E., Zemzyulina V.YU., Pelymskaya I.S. [Study of the market structure of the Russian automotive industry: trends and prospects]. Kreativnaya ekonomika, 2024, vol. 18, no. 12, pp. 3383–3406. (In Russ.) DOI: 10.18334/ce.18.12.122189 EDN: LUZJGB
Mikhailenko D.I. [Statistics and analysis of the automobile market in Russia]. Vestnik nauki, 2023, no. 6, pp. 189–195. (In Russ.) EDN: LZZETZ
Smelkov K.A. [Global passenger car market: competition as a driving force for the development of potential opportunities for companies]. Fundamental'nye issledovaniya, 2025, no. 5, pp. 95–101. (In Russ.) DOI: 10.17513/fr.43838 EDN: OOHYGQ
Ogneva E.D. Automotive industry digitalization: effect on the labor market, business models and consumer behavior. Nauchnyi zhurnal molodykh uchenykh, 2024, no. 3, pp. 89–91. EDN: EKZEJQ
Milyakin S.R., Skubachevskaya N.D., Migal' A.V. [The passenger car market in Russia: history, current status and forecast]. Problemy prognozirovaniya, 2025, no. 1, pp. 137–150. (In Russ.) DOI: 10.47711/0868-6351-208-137-150 EDN: AAQNTD
Dontsova O.I., Klimonov D.V. [Prospects for the development of the international automotive market]. Ekonomika, predprinimatel'stvo i pravo, 2023, vol. 13, no. 9, pp. 3397–3412. (In Russ.) DOI: 10.18334/epp.13.9.118275 EDN: LSQCTZ
D'yachenko N.S. [Analysis of prospects of development of electric vehicles in Russia]. Vestnik nauki, 2025, vol. 21, no. 6, pp. 2306–2312. (In Russ.) EDN: LQGENO
Pirogova O.E., Shishova M.O. [The use of logistic regression to assess the financial condition of enterprises]. Innovatsionnaya ekonomika: perspektivy razvitiya i sovershenstvovaniya, 2016, no. 5, pp. 114–122. (In Russ.) EDN: WMNGFB
Matraeva L.V. [Use of logistic regression in identifying priorities for regional investment policy in respect of foreign investors in the regions of the Russian Federation]. Statistika i matematicheskie metody v ekonomike, 2013, no. 6, pp. 170–174. (In Russ.) EDN: RPKPQV
Tyrsin A.N., Vasil'eva E.V. [A binary logistic regression as a management model on the example of improving the quality of life of the population]. Fundamental'nye issledovaniya, 2020, no. 10, pp. 96–102. (In Russ.) DOI: 10.17513/fr.42862 EDN: VHENEK
Ustinov D.A., Emel'yantsev D.O., Durov I.V., Tatarenkov A.S. [Automation of pricing in retail using machine learning]. Universum: tekhnicheskie nauki, 2024, no. 6, pp. 20–26. (In Russ.) DOI: 10.32743/UniTech.2024.123.6.17762 EDN: SKSABX
Lixian Qian, Soopramanien D. Using diffusion models to forecast market size in emerging markets with applications to the Chinese car market. Journal of Business Research, 2014, vol. 67, iss. 6, pp. 1226–1232. DOI: 10.1016/j.jbusres.2013.04.008
Dong Guo, Wei Yan, Xingbang Gao et al. Forecast of passenger car market structure and environmental impact analysis in China. Science of the Total Environment, 2021, vol. 772, no. 144950. DOI: 10.1016/j.scitotenv.2021.144950 EDN: ZEQJUN
Ziye Lin. Analysis of the Used Car Market in the United States. BCP Business & Management, 2022, vol. 29, pp. 99–105. DOI: 10.54691/bcpbm.v29i.2193 EDN: YBPKZU
Domarchi C., Cherchi E.. Role of car segment and fuel type in the choice of alternative fuel vehicles: A cross-nested logit model for the English market. Applied Energy, 2024, vol. 357, no. 122451. DOI: 10.1016/j.apenergy.2023.122451 EDN: XWTTLS
Wentao He, Xiaoli Hao. Competition and welfare effects of introducing new products into the new energy vehicle market: Empirical evidence from Tesla's entry into the Chinese market. Transportation Research Part A: Policy and Practice, 2023, vol. 174, no. 103730. DOI: 10.1016/j.tra.2023.103730 EDN: QZKUXS
Orlova I.V. [Using the prophet package in time series forecasting]. Fundamental'nye issledovaniya, 2021, no. 3, pp. 94–102. (In Russ.) DOI: 10.17513/fr.42987 EDN: KPRAPD
