A Study of the Potential of ChatGPT-5 for Econometric Modelling of Organizational Innovation Performance: Methodological Foundations and Comparative Analysis of Experimental Results

This article explores the feasibility of using the ChatGPT artificial intelligence (AI) for econometric modelling of Russian organizations’ innovation performance. The study’s relevance stems from the need to modernize traditional econometric tools to handle growing data sets. The aim of the study is to provide methodological justification and experimental verification of the feasibility of using ChatGPT-5 for comprehensive econometric modelling of organizations’ innovation performance. The methodological framework was based on a comparative approach implemented using official Rosstat data for 2010–2024. The experiment included a correlation and regression analysis for three key indicators: the organization’s level of innovation performance, the volume of innovative product output, and the number of advanced manufacturing technologies developed. A total of 15 observations were conducted on three indicators. Calculation results obtained in the standard Excel Data Analysis package were compared with ChatGPT-5 analytics generated through the Python interpreter. The experiment confirmed the complete identity of the quantitative calculations between the Excel Data Analysis package and the AI model. ChatGPT-5 enabled the accurate interpretation of statistical metrics (p-values, R-squared, etc.), identified limitations of regression models, and generated recommendations for their improvement. It was found that the key drivers of organizational innovation are innovation expenditures in Russian organizations, the Inventive Activity Index (patent activity), and federal research funding. In conclusion, three scenarios for the development of organizational innovation through 2035 were proposed. It is concluded that ChatGPT-5 is highly applicable as an intelligent assistant in econometric modelling, provided that methodological limitations are observed.

1. Arzhaev F.I., Kokarev M.A. (2023) The Potential of Neural Network Models on the Example of ChatGPT: Opportunities, Limitations and Application in the Analysis of Foreign Trade. Rossiyskiy vneshneekonomicheskiy vestnik. Vol. 12. P. 87–100. DOI: 10.24412/2072–s8042–s2023–s12–s87–s100

2. Astrakhantseva I.A., Gerasimov A.S., Smirnova O.P. (2024) Evaluating Statistical and Machine Learning Models for Inflation Forecasting. Sovremennyye naukoyemkiye tekhnologii. Regional’noye prilozheniye. No. 3(79). P. 120–131. DOI: 10.6060/snt.20247903.0019

3. Byvshev V.I., Suslova Yu.Yu., Voloshin A.V., Pisarev I.V. (2025) The Genesis of Innovations and Innovative Development. Vestnik OmGU. Seriya: Ekonomika. Vol. 23. No. 1. P. 16–27. DOI: 10.24147/1812–s3988.2025.23(1).16–s27

4. Cheng Y., Zeng Y., Zou J. (2024) Harnessing ChatGPT for Predictive Financial Factor Generation: A New Frontier in Financial Analysis and Forecasting. The British Accounting Review. Vol. 58. Is. 2. DOI: 10.1016/j.bar.2024.101507

5. Dmitriev S.G. (2025) Methodological Parallels: Economic Theory and Interpretability of Artificial Intelligence Models. Kant. No. 1(54). P. 28–33. DOI: 10.24923/2222–s243X.2025–s54.5

6. Imamov M.M. (2023) Using ChatGPT in Economics. Diskussiya. No. 4(119). P. 62–72. DOI: 10.46320/2077–s7639–s2023–s4-119–s62–s72

7. Just J. (2024) Natural Language Processing for Innovation Search — Reviewing an Emerging Non-Human Innovation Intermediary. Technovation. Vol. 129. DOI: 10.1016/j.technovation.2023.102883

8. Kassa B.Y., Worku E.K. (2025) The Impact of Artificial Intelligence on Organizational Performance: The Mediating Role of Employee Productivity. Journal of Open Innovation: Technology, Market, and Complexity. Vol. 11. Is. 1. DOI: 10.1016/j.joitmc.2025.100474

9. Kirichenko A.O., Zolkin A.L., Sverdlikova E.A., Podolko P.M. (2024) Methods and Possibilities of Using Artificial Intelligence in the Analysis of Economic Trends. Prikladnyye ekonomicheskiye issledovaniya. No. 1. P. 177–184. DOI: 10.47576/2949–s1908.2024.1.1.022

10. Kiselev R.O. (2024) Innovatsionnaya aktivnost’ kak kompetentsiya deyatel’nosti organizatsii [Innovative activity as a competence of an organization’s activities]. Uchenyye zapiski Krymskogo federal’nogo universiteta imeni V.I. Vernadskogo. Ekonomika i upravleniye. Vol. 10. No. 4. P. 39–48.

11. Lozhkina S.L., Novikova E.V., Karpenko A.V. (2025) Analytical Potential of Innovative Activities of Industrial Organizations. Yestestvenno-gumanitarn·yye issledovaniya. No. 3(59). P. 307–311.

12. Ovchinnikova A. V., Dorf E. A. (2024) The Evolution of the Theory of Innovations. Vestnik Yuzhno-Ural’skogo gosudarstvennogo universiteta. Seriya: Ekonomika i menedzhment. Vol. 18. No. 1. P. 160–169. DOI: 10.14529/em240115

13. Plakhova S.E., Melikova Yu.B., Rudnev S.G., Kovaleva K.A. (2023) Application of Artificial Intelligence Methods in Macroeconomic Forecasting. Zhurnal prikladnykh issledovaniy. No. S1. P. 65–72. DOI: 10.47576/2949–s1878_2023_S1_65

14. Poskochinova O.G., Murashov D.S. (2024) Innovation Management in the Modern Economy and Factors Stimulating the Processes of Innovative Development of Russia. Progressivnaya ekonomika. No. 10. P. 175–186. DOI: 10.54861/27131211_2024_10_175

15. Schumpeter J. (1982) Theorie der wirtschaftlichen Entwicklung. Moscow: Progress.

16. Shapovalov V.V. (2024) Major Innovations Theories of the 20th Century (Part 1). Vestnik Tomskogo gosudarstvennogo universiteta. Ekonomika. No. 66. P. 345–353. DOI: 10.17223/19988648/66/22

17. Yang K., Deng R., Wei Y., Wang S. (2025) The Power of ChatGPT in Processing Text: Evidence from Analysis and Prediction in the Exchange Rate Markets. Financial Innovation. Vol. 11. DOI: 10.1186/s40854–s025–s00789–s6

18. Zakhem N.B., Diab M.B., Tahan S.A (2025) Cross-Disciplinary Academic Evaluation of Generative AI Models in HR, Accounting, and Economics: ChatGPT-5 vs. DeepSeek. Administrative Sciences. Vol. 15. Is. 11. DOI: 10.3390/admsci15110412

19. Zhang B. (2024) GPT in Finance Forecasting. Advances in Economics Management and Political Sciences. Vol. 99. P. 73–80. DOI: 10.54254/2754–s1169/99/2024OX0199

20. Zhang G., Lu C., Luo Q. (2025) Application of Large Language Models in the AECO Industry: Core Technologies, Application Scenarios, and Research Challenges. Buildings. Vol. 15. Is. 11. DOI: 10.3390/buildings15111944