Issue: № 2, 2025
Doi: https://doi.org/10.37634/efp.2025.2.19
Introduction. Neural networks are transforming business decision-making by enabling organizations to process vast amounts of data, identify patterns, and automate strategic processes. Their applications span various industries, including market analysis, financial forecasting, risk management, production optimization, and personalized recommendations. Despite their advantages, challenges such as data quality requirements, model interpretability, cybersecurity risks, and ethical concerns limit their widespread adoption. This purpose of the paper is to analyze the role of neural networks in decision-making, assess their impact on business efficiency, and identify key challenges and future prospects. The research explores how AI-driven solutions optimize operations, mitigate risks, and enhance strategic planning, focusing on their integration with corporate systems and hybrid modeling approaches. Results. Findings indicate that neural networks significantly improve decision-making across various domains by increasing forecasting accuracy, automating processes, and enhancing risk management. AI-powered models contribute to demand prediction, fraud detection, supply chain optimization, and real-time financial analytics. However, issues related to data dependency, explainability, and security remain critical barriers. The study highlights the growing role of cloud computing and hybrid AI models in overcoming these limitations. The prospects for the further development of neural networks in decision-making processes have been substantiated, highlighting their strategic importance in enhancing management efficiency, minimizing risks, and creating competitive advantages. Conclusions. While challenges persist, neural networks continue to evolve, driven by advancements in AI, big data analytics, and cloud-based solutions. Their integration into enterprise management systems enhances automation and predictive capabilities, offering businesses a competitive edge. Future developments in hybrid AI approaches and explainable AI will further refine decision-making accuracy and reliability, ensuring more ethical and transparent applications in business environments.
Keywords : artificial intelligence, decision-making, neural networks
References:
1. Hrinchenko R.V., Kyslychko K.A., Nechepeliuk V.H., Onyshchuk V.S. Prerequisites for enterprise adaptation to changes during the war period. Scientific Bulletin of Odesa National Economic University. 2023. No. 5–6 (306–307). pp. 91–100. (in Ukrainian).
2. Malynovska, Y., Petryshyn, N., Malynovskiy, Y., Oliinyk, A. Approaches to the development of business growth strategy. Journal of Vasyl Stefanyk Precarpathian National University. 2017. Vol. 4, No. 3–4. pp. 88–94.
3. Kutsyk P., Kovtun O. Identification of promising business and modeling of optimal strategic sets for enterprises using artificial intelligence capabilities. Digital Economy and Economic Security. 2024. No. 5(14). pp. 127–136. (in Ukrainian).
4. Bashynska I., Prokopenko O. Leveraging artificial intelligence for circular economy: transforming resource management, supply chains, and manufacturing practices. Scientific Journal of Bielsko-Biala School of Finance and Law. 2024. No. 28(2). pp. 85–91.
5. Kopiika O.V. Geoinformatics in decision-making support systems. Scientific Notes of Junior Academy of Sciences of Ukraine. 2024. No. 2(30). pp. 37–47.
6. Tiukhtenko N.A., Serezhenkova O.I. Digital transformation of the entrepreneurial environment in the context of socio-cultural changes in modern business. Economic Synergy. 2024. No. 4. pp. 8–21. (in Ukrainian).
7. Pimenov S.A. Investments in artificial intelligence: value, feasibility, and scaling in the context of enterprise digitalization. Investments: Practice and Experience. 2024. No. 22. pp. 112–120. (in Ukrainian).
8. Koretska N., Feshchuk A., Tomsha K. Evaluation of the quality of managerial decisions at the enterprise. Economic Forum. 2021. No. 2(2). pp. 88–100. (in Ukrainian).