N.E. Sadkovskaya1, A.N. Manin2, A.P. Gorshkova3, A.V. Prudnikov4
1–4 Moscow Aviation University (National Research University) (Moscow, Russia)

1 natsadkovskaya@rambler.ru, 2 andreym012@gmail.com, 3 alyaayg@yandex.ru, 4 AlexPrudnikov1@yandex.ru

In recent years, startups have become a critical driver of innovation and economic growth. Despite the availability of various support programs, many startups still face significant challenges in achieving success. Evaluating the potential of startups remains a complex task, involving the consideration of multiple factors, including market dynamics, competitive landscape, and business model viability. Traditional analysis methods often fail to account for the complexity of these factors, especially when dealing with unstructured data such as textual information from investor pitches, social media, and financial reports. The rapid development of machine learning (ML) and artificial intelligence (AI) techniques provides a new avenue for improving the efficiency and effectiveness of startup analysis. However, practical application of these methods requires careful evaluation of their feasibility and real-world effectiveness, particularly when dealing with the inherent uncertainties in the startup ecosystem.

The objective of this study is to assess the feasibility of applying ML and AI methods for analyzing the success of startups, with an emphasis on evaluating their practical applicability in real-world scenarios. The goal is not to develop highly accurate predictive models but rather to explore the potential of these methods in improving the decision-making process and providing actionable insights for investors, accelerators, and other stakeholders.

In the study authors have conducted experiments using various machine learning and artificial intelligence techniques to analyze both qualitative (textual) and quantitative (financial, market) data from startups. The results have demonstrated that while AI methods can yield promising insights and forecasts, their practical utility and accuracy are influenced by several factors, including data quality, the market environment, and the availability of relevant variables. These methods could be useful for preliminary screening and identifying potential high-growth startups. But further refinement and adjustments are needed to enhance decision-making and improve the accuracy of predictions. The results suggest that ML and AI methods can play a significant role in improving the process of initial startup evaluation, providing valuable insights for investors and accelerators. They can assist in identifying trends, making informed decisions, and offering recommendations based on data-driven insights. However, for these methods to be truly effective, it is essential to address challenges related to data quality, sector-specific factors, and model customization. Future research and development in this area could lead to more reliable and robust tools for assessing startup success, ultimately contributing to more informed investment strategies and innovation management.

Sadkovskaya N.E., Manin A.N., Gorshkova A.P., Prudnikov A.V. Practical application of machine learning and artificial intelligence methods in primary analysis of startup success. Neurocomputers. 2025. V. 27. № 2. P. 13–22. DOI: https://doi.org/10.18127/j19998554-202502-02 (in Russian)

1. Golovashkina A.A. Osobennosti zapuska startapov: problemy, faktory, nyuansy. Molodoj uchenyj. 2023. № 23 (470). S. 237–241. (in Russian)
2. RB CHOICE – 100 perspektivnykh rossijskikh startapov [Elektronnyj resurs]. URL: https://rb.ru/list/rb-choice-100-2022/ (data obrash­cheniya: 29.11.2024). (in Russian)
3. RB CHOICE – 100 perspektivnykh rossijskikh startapov 2023 goda [Elektronnyj resurs]. URL: https://rb.ru/longread/rb-choice-100-2023/ (data obrashcheniya: 29.11.2024). (in Russian)
4. Sataev P.A. Rekomendatsii po razvitiyu startapa s uchetom znachimykh faktorov. Izvestiya SPBGEU. 2022. № 3 (135) [Elektronnyj resurs]. URL: https://cyberleninka.ru/article/n/rekomendatsii-po-razvitiyu-startapa-s-uchetom-znachimyh-faktorov (data obrashcheniya: 29.11.2024). (in Russian)
5. Hota S.L., Mohanty N., Kumar A., Panda K. Achieving sustainability in newly founded start-up businesses: Navigating challenges and gaining insights. Recoletos Multidisciplinary Research Journal. V. 12. № 1. P. 1–7. DOI: 10.32871/rmrj2412.01.01.
6. Raeva I.V. Startap: ponyatie, osobennosti, metody otsenki. Imushchestvennye otnosheniya v RF. 2021. № 6 (237) [Elektronnyj resurs]. URL: https://cyberleninka.ru/article/n/startap-ponyatie-osobennosti-metody-otsenki (data obrashcheniya: 30.11.2024). (in Russian)
7. Kol'tsov M.A., Sidorov D.V., Sokolov I.N. «Innoterms» kak instrument preodoleniya translyatsionnogo bar'era, voznikayushchego mezhdu uchastnikami innovatsionnogo protsessa. Innovatsii. 2016. № 12 (218) [Elektronnyj resurs]. URL: https://cyberleninka.ru/article/n/innoterms-kak-instrument-preodoleniya-translyatsionnogo-bariera-voznikayuschego-mezhdu-uchastnikami-innovatsionnogo-protsessa (data obrashcheniya: 30.11.2024). (in Russian)
8. Kozhanova A.V. Mekhanizm finansirovaniya rossijskikh startapov na raznykh stadiyakh ikh zhiznennogo tsikla. Diss. … kand. ekon. nauk. M. 2021. (in Russian)
9. Trusova Yu.A., Il'ina A.I. Metodologiya vnedreniya mashinnogo obucheniya v bankovskoj sfere. Vestnik Samarskogo universiteta. Ekonomika i upravlenie. 2023. № 4 [Elektronnyj resurs]. URL: https://cyberleninka.ru/article/n/metodologiya-vnedreniya-mashinnogo-obucheniya-v-bankovskoy-sfere (data obrashcheniya: 02.12.2024). (in Russian)
10. Divyashree S., Joshua C.J., Md A.Q. et al. Enabling business sustainability for stock market data using machine learning and deep learning approaches. Annals of Operations Research. 2024. V. 342. P. 287–322. DOI: 10.1007/s10479-024-06118-x.
11. Siddiqui D., Mumtaz U., Ahmad N. Artificial intelligence in entrepreneurship: A bibliometric analysis of the literature. Journal of Global Entrepreneurship Research. 2024. V. 14. DOI: 10.1007/s40497-024-00385-5.
12. Bidgoli M.R., Vanani I.R., Goodarzi M. Predicting the success of startups using a machine learning approach. Journal of Innovation and Entrepreneurship. 2024. V. 13. DOI: 10.1186/s13731-024-00436-x.
13. Kalbande S., Karmore R. Startup success prediction using machine learning. In: Swaroop A., Kansal V., Fortino G., Hassanien A.E. (Eds.) Proceedings of Fifth Doctoral Symposium on Computational Intelligence (DoSCI-2024). Lecture Notes in Networks and Systems. 2024. V. 1086. Springer, Singapore. DOI: 10.1007/978-981-97-6036-7_26.
14. Koval'kov D.V. Iskusstvennyj intellekt v biznes-analize i ego tsennost' ispol'zovaniya v biznese. Vestnik nauki. 2024. № 6 (75) [Elektronnyj resurs]. URL: https://cyberleninka.ru/article/n/iskusstvennyy-intellekt-v-biznes-analize-i-ego-tsennost-ispolzovaniya-v-biznese (data obrashcheniya: 03.12.2024). (in Russian)
15. Python 3.12.7 documentation [Elektronnyj resurs]. URL: https://docs.python.org/3.12/.
16. Matplotlib 3.9.3 documentation [Elektronnyj resurs]. URL: https://matplotlib.org/stable/index.html.