NEURAL NETWORK TECHNOLOGIES AS A KEY DETERMINANT OF FORECASTING ACCURACY OF FINANCIAL LOSSES FROM CYBER THREATS
Abstract
The article examines the key factors determining the accuracy of forecasting financial losses from cyber threats using neural network technologies. In the context of rapid digitalization and ongoing hybrid aggression against Ukraine, the problem of reliable assessment and forecasting of financial losses has gained strategic importance for national security. The study aims to provide a comprehensive analysis of how the evolution of neural network architectures, data availability and quality, computational resources, and domain expertise influence the performance and reliability of predictive models. The research is based on the analysis of scientific literature and official CERT-UA reports for 2021-2024, which highlight the limitations of traditional forecasting approaches. A theoretical and methodological framework is employed to identify the relationships between key factors affecting forecasting accuracy. The findings indicate that predictive performance is driven by the synergy of three core components: data quality and volume, computational capacity, and expert knowledge. It is demonstrated that modern neural network architectures, including LSTM and Transformer models, significantly outperform traditional methods in capturing nonlinear dependencies and latent patterns. The study substantiates that the effective implementation of neural network-based forecasting systems in Ukraine requires a comprehensive approach, including the development of a national data infrastructure, investment in high-performance computing, and the advancement of specialized expertise. The proposed recommendations take into account the specific threat landscape and structural characteristics of the Ukrainian economy. Enhancing model transparency and interpretability, as well as strengthening international cooperation, are identified as critical prerequisites for increasing trust in forecasting results and their practical application.
References
Полігенько О. Кібератака на Україну: від держреєстрів до Monobank. Як бізнесу захиститися, не втратити дані і працездатність. Forbes.ua. 2025. URL: https://forbes.ua/innovations/kiberriziki-na-ponad-10-trln-zbitkiv-yaki-galuzi-biznesu-naybilshe-atakuyut-kiberzlochintsi-ta-yak-minimizuvati-naslidki-instruktsiya-vid-eksperta-u-sferi-kiberbezpeki-olega-poligenko-23012025-26534
World Bank. A review of the economic costs of cyber incidents. 2024. URL: https://documents.worldbank.org/en/publication/documents-reports/documentdetail/099092324164536687/p17876919ffee4079180e81701969ad0a18
CERT-UA. 2025. URL: https://cert.gov.ua/
World Economic Forum. Global cybersecurity outlook 2025. 2025. URL: https://www.weforum.org/publications/global-cybersecurity-outlook-2025/
Department for Science, Innovation and Technology. Research on the cyber security of AI. 2024. URL: https://www.gov.uk/government/publications/research-on-the-cyber-security-of-ai
European Union Agency for Cybersecurity (ENISA). Risk management. URL: https://www.enisa.europa.eu/topics/risk-management
Боженко В. В., Пахненко О. М., Яровенко Г. М., Койбічук В. В. Інструменти аналізу даних для оцінки кіберризиків у фінансових послугах. Здобутки економіки: перспективи та інновації. 2025. № 20. DOI: https://doi.org/10.5281/zenodo.16509500
Гончаренко І. Кіберзагрози фінансового сектора в умовах війни. Економіка та суспільство. 2023. № 50. DOI: https://doi.org/10.32782/2524-0072/2023-50-82
Криклій О. А. Теорія та практика забезпечення кіберстійкості банків. Ефективна економіка. 2020. № 10. DOI: https://doi.org/10.32702/2307-2105-2020.10.504
Трусова Н. В., Чкан І. О. Кіберзахист банківської системи України в умовах цифрових трансформацій. Збірник наукових праць ТДАТУ. 2023. № 1(47). С. 151-163. DOI: https://doi.org/10.31388/2519-884X-2023-47-151-163
Тищенко С. І., Пархоменко О. Ю., Дармосюк В. М. Моделювання та аналіз ризиків кібератак на фінансові установи з використанням методів математичної статистики та Python. Modern Economics. 2024. № 48. С. 130-136. DOI: https://doi.org/10.31521/modecon.V48(2024)-166
Фаріон В., Гомотюк А., Назар Р., Турчин С. Використання штучного інтелекту для прогнозування фінансових показників. Економічний аналіз. 2024. Т. 34. № 2. С. 327–337. DOI: https://doi.org/10.35774/econa2024.02.327
Hoang D., Wiegratz K. Machine learning methods in finance: Recent applications and prospects. European Financial Management. 2023. Vol. 29, No. 5. DOI: https://doi.org/10.1111/eufm.12408
Javaid H. A. AI-driven predictive analytics in finance: Transforming risk assessment and decision-making. Advances in Computer Sciences. 2024. Vol. 7, No. 1. URL: https://acadexpinnara.com/index.php/acs/article/view/204
Al-E’mari S., Sanjalawe Y., Al-E’mari A. The role of artificial intelligence in enhancing financial decision-making and administrative efficiency: A systematic review. Al-Basaer Journal of Business Research. 2025. Vol. 1, No. 1. DOI: https://doi.org/10.71202/paper21
Sako K., Mpinda B. N., Rodrigues P. C. Neural networks for financial time series forecasting. Entropy. 2022. Vol. 24, No. 5. Art. 657. DOI: https://doi.org/10.3390/e24050657
Tiwo O. J. Quantum machine learning for secure financial forecasting: Mitigating data breaches and adversarial exploits. Asian Journal of Research in Computer Science. 2025. Vol. 18, No. 4. P. 154-175. DOI: https://doi.org/10.9734/ajrcos/2025/v18i4613
Thakkar S., Kazdaghli S., Mathur N., et al. Improved financial forecasting via quantum machine learning. Quantum Machine Intelligence. 2024. Vol. 6, No. 1. DOI: https://doi.org/10.1007/s42484-024-00157-0
Xu Z., Wang Y., Feng X., et al. Quantum-enhanced forecasting: Leveraging quantum gramian angular field and CNNs for stock return predictions. Finance Research Letters. 2024. Vol. 67. Art. 105840. DOI: https://doi.org/10.1016/j.frl.2024.105840
Obioha-Val O. A., Lawal T. I., Olaniyi O. O., et al. Investigating the feasibility and risks of leveraging artificial intelligence and open source intelligence to manage predictive cyber threat models. Journal of Engineering Research and Reports. 2025. Vol. 27, No. 2. P. 10-28. DOI: https://doi.org/10.9734/jerr/2025/v27i21390
Eling M., Elvedi M., Falco G. The economic impact of extreme cyber risk scenarios. North American Actuarial Journal. 2022. Vol. 27, No. 3. P. 429–443. DOI: https://doi.org/10.1080/10920277.2022.2034507
Kyivstar Business Hub. Microsoft digital defense report 2024: Ключові інсайти у глобальній індустрії кібербезпеки. 2024. URL: https://hub.kyivstar.ua/articles/microsoft-digital-defense-report-2024-klyuchovi-insajti-u-globalnij-industriyi-kiberbezpeki
Субботін С. О. Нейронні мережі: теорія та практика: навч. посіб. Житомир: Вид. О. О. Євенок, 2020. 184 с.
Hakim L., Wulandhari L. A. Cyber security threat prediction using time-series data with LSTM algorithms. Indonesian Journal of Electrical Engineering and Informatics. 2024. Vol. 12, No. 4. P. 1111-1133. DOI: https://doi.org/10.52549/ijeei.v12i4.5648
Santoso J., Hartono B., Silalahi F., Muthohir M. Transformers in cybersecurity: Advancing threat detection and response through machine learning architectures. Journal of Technology Informatics and Engineering. 2024. Vol. 3, No. 3. P. 382-396. DOI: https://doi.org/10.51903/jtie.v3i3.211
Kabir M. R., Bhadra D., Ridoy M., Milanova M. LSTM-Transformer-based robust hybrid deep learning model for financial time series forecasting. Sci. 2024. Vol. 7, No. 1. Art. 7. DOI: https://doi.org/10.3390/sci7010007
Бебешко Б. Т. Навчання штучної нейронної мережі на основі даних оцінювання результативності та ризиків інвестування в цифрові активи. Кібербезпека: освіта, наука, техніка. 2023. № 3(19). С. 135-145. DOI: https://doi.org/10.28925/2663-4023.2023.19.135145
Polihenko, O. (2025). Cyberattack on Ukraine: From state registers to Monobank. How businesses can protect themselves, avoid losing data and efficiency. Forbes.ua. Available at: https://forbes.ua/innovations/kiberriziki-na-ponad-10-trln-zbitkiv-yaki-galuzi-biznesu-naybilshe-atakuyut-kiberzlochintsi-ta-yak-minimizuvati-naslidki-instruktsiya-vid-eksperta-u-sferi-kiberbezpeki-olega-poligenko-23012025-26534
World Bank. (2024). A review of the economic costs of cyber incidents. Available at: https://documents.worldbank.org/en/publication/documents-reports/documentdetail/099092324164536687/p17876919ffee4079180e81701969ad0a18
CERT-UA. (2025). cert.gov.ua. Available at: https://cert.gov.ua/
World Economic Forum. (2025). Global cybersecurity outlook 2025. Available at: https://www.weforum.org/publications/global-cybersecurity-outlook-2025/
Department for Science, Innovation and Technology. (2024). Research on the cyber security of AI. GOV.UK. Available at: https://www.gov.uk/government/publications/research-on-the-cyber-security-of-ai
European Union Agency for Cybersecurity. (n.d.). Risk management. Available at: https://www.enisa.europa.eu/topics/risk-management
Bozhenko, V. V., Pakhnenko, O. M., Yarovenko, H. M., & Koibichuk, V. V. (2025). Data mining tools for cyber risk assessment in financial services. Economic achievements: prospects and innovations, 20. DOI: https://doi.org/10.5281/zenodo.16509500
Honcharenko, I. (2023). Cyber threats of the financial sector in the conditions of war. Economy and Society, 50. DOI: https://doi.org/10.32782/2524-0072/2023-50-82
Kryklii, O. A. (2020). Theory and practice of ensuring cyber resilience of banks. Efficient economy, 10. DOI: https://doi.org/10.32702/2307-2105-2020.10.504
Trusova, N. V., & Chkan, I. O. (2023). Cyber protection of the banking system of Ukraine in conditions of digital transformations. Scientific bulletin of the Tavria State Agrotechnological University, 1(47), 151-163. DOI: https://doi.org/10.31388/2519-884X-2023-47-151-163
Tyshchenko, S. I., Parkhomenko, O. Yu., & Darmosyuk, V. M. (2024). Modeling and analysis of risks of cyberattacks on financial institutions using methods of mathematical statistics and Python. Modern Economics, 48, 130-136. DOI: https://doi.org/10.31521/modecon.V48(2024)-166
Farion, V., Homotiuk, A., Nazar, R., & Turchyn, S. (2024). Use of artificial intelligence for forecasting financial indicators. Economic analysis, 34(2), 327-337. DOI: https://doi.org/10.35774/econa2024.02.327
Hoang, D., & Wiegratz, K. (2023). Machine learning methods in finance: Recent applications and prospects. European Financial Management, 29(5). DOI: https://doi.org/10.1111/eufm.12408
Javaid, H. A. (2024). AI-driven predictive analytics in finance: Transforming risk assessment and decision-making. Advances in Computer Sciences, 7(1). Available at: https://acadexpinnara.com/index.php/acs/article/view/204
Al-E’mari, S., Sanjalawe, Y., & Al-E’mari, A. (2025). The role of artificial intelligence in enhancing financial decision-making and administrative efficiency: A systematic review. Al-Basaer Journal of Business Research, 1(1). DOI: https://doi.org/10.71202/paper21
Sako, K., Mpinda, B. N., & Rodrigues, P. C. (2022). Neural networks for financial time series forecasting. Entropy, 24(5), 657. DOI: https://doi.org/10.3390/e24050657
Tiwo, O. J. (2025). Quantum machine learning for secure financial forecasting: Mitigating data breaches and adversarial exploits. Asian Journal of Research in Computer Science, 18(4), 154-175. DOI: https://doi.org/10.9734/ajrcos/2025/v18i4613
Thakkar, S., Kazdaghli, S., Mathur, N., Kerenidis, I., Ferreira-Martins, A. J., & Brito, S. (2024). Improved financial forecasting via quantum machine learning. Quantum Machine Intelligence, 6(1). DOI: https://doi.org/10.1007/s42484-024-00157-0
Xu, Z., Wang, Y., Feng, X., Wang, Y., Li, Y., & Lin, H. (2024). Quantum-enhanced forecasting: Leveraging quantum gramian angular field and CNNs for stock return predictions. Finance Research Letters, 67, 105840. DOI: https://doi.org/10.1016/j.frl.2024.105840
Obioha-Val, O. A., Lawal, T. I., Olaniyi, O. O., Gbadebo, M. O., & Olisa, A. O. (2025). Investigating the feasibility and risks of leveraging artificial intelligence and open source intelligence to manage predictive cyber threat models. Journal of Engineering Research and Reports, 27(2), 10-28. DOI: https://doi.org/10.9734/jerr/2025/v27i21390
Eling, M., Elvedi, M., & Falco, G. (2022). The economic impact of extreme cyber risk scenarios. North American Actuarial Journal, 27(3), 429-443. DOI: https://doi.org/10.1080/10920277.2022.2034507
Kyivstar Business Hub. (2024). Microsoft digital defense report 2024: Key insights into the global cybersecurity industry. Available at: https://hub.kyivstar.ua/articles/microsoft-digital-defense-report-2024-klyuchovi-insajti-u-globalnij-industriyi-kiberbezpeki
Subbotin, S. O. (2020). Neural networks: theory and practice. Zhytomyr: Publishing house O. O. Evenok.
Hakim, L., & Wulandhari, L. A. (2024). Cyber security threat prediction using time-series data with LSTM algorithms. Indonesian Journal of Electrical Engineering and Informatics, 12(4), 1111-1133. DOI: https://doi.org/10.52549/ijeei.v12i4.5648
Santoso, J., Hartono, B., Silalahi, F., & Muthohir, M. (2024). Transformers in cybersecurity: Advancing threat detection and response through machine learning architectures. Journal of Technology Informatics and Engineering, 3(3), 382-396. DOI: https://doi.org/10.51903/jtie.v3i3.211
Kabir, M. R., Bhadra, D., Ridoy, M., & Milanova, M. (2024). LSTM-Transformer-based robust hybrid deep learning model for financial time series forecasting. Sci, 7(1), 7. DOI: https://doi.org/10.3390/sci7010007
Bebeshko, B. (2023). Artificial neural network training based on performance and risks assessment data of the investment in digital assets. Cybersecurity: Education, Science, Technique, 3(19), 135-145. DOI: https://doi.org/10.28925/2663-4023.2023.19.135145
Copyright (c) 2026 Антон Бойко, Олександр Кушнерьов, Дмитро Ліхолєтов
This work is licensed under a Creative Commons Attribution 4.0 International License.
