In this study, it was analyzed the ability to forecast the revenues of major corporations such as Apple, Amazon, GE, IBM, and ExxonMobil using Random Forest and XGBoost machine learning algorithms, as well as Tableau as a benchmark analytics tool. The main objective was to assess the accuracy of these methods and their capability to predict financial indicators based on historical data. Google Colab was used as the computational environment, which enabled seamless integration of algorithms, handling of large datasets, and rapid model testing. Revenue data for the companies were entered into Google Sheets and then imported for further analysis. Various data preprocessing techniques, including scaling and anomaly removal, were applied. The results showed that while no model achieved perfect accuracy, machine learning demonstrated competitiveness compared to Tableau. For instance, XGBoost provided a more accurate revenue prediction for GE (13.02% relative error vs. 24.06% in Tableau), while Random Forest performed better for ExxonMobil (3.82% vs. 16.95%). At the same time, Tableau delivered better results for Amazon and Apple, which may be due to the specifics of its internal forecasting algorithms. The analysis of the Mean Squared Error (MSE) confirmed that prediction accuracy varies depending on the chosen model. Random Forest had an MSE of 3649.4, while XGBoost had 3713.4, indicating the need for further optimization of model parameters. However, considering that even Tableau exhibited significant deviations in forecasts, it can be concluded that machine learning methods are promising and can be used for financial forecasting, especially after further refinement and adaptation to specific tasks. Thus, our research confirms that Random Forest and XGBoost are effective analytical tools that can compete with traditional visualization and forecasting methods. Future research can focus on improving model parameters and incorporating additional factors that influence corporate financial performance.
[1] S. Meharanjunisa, “Forecasting of Artificial Intelligence and its Influence on Revenue”, IJIRT, 2020, 805p. https://www.researchgate.net/profile/Syed-Meharanjunisa/publication/342899047 _Forecasting_of_Artificial_Intelligence_and_its_Influence_ on_Revenue/links/5f0c7f2992851c38a519c12f/Forecasting-of-Artificial-Intelligence-and-its-Influence-on-Revenue.pdf?cfchltk= 4nUEBO2rjmTprsL_nCPPjQPOH1IRCiYBUTFC6eRRcwY-1737628845-1.0.1.1-cx0yAeekyh7WI8sCDf0bIS4Q.AOOc_L gBpTlhtKyk4I
[2] V. Golderzahi, H. K. Pao, “Revenue forecasting in smart retail based on customer clustering analysis”, Internet of Things, Volume 27, 2024, 101286. https://doi.org/10.1016/j.iot.2024.101286
[3] M. Würfel, Q. Han, M. Kaiser, “Online Advertising Revenue Forecasting: An Interpretable Deep Learning Approach”, IEEE International Conference on Big Data (Big Data), 2021, Orlando, FL, USA, pp. 1980-1989, https://arxiv.org/pdf/2111.08840
[4] N. Groene, S. Zakharov, “Introduction of AI‑based sales forecasting: how to drive digital transformation in food and beverage outlets”, Discov Artif Intell 4, 1 (2024). https://doi.org/10.1007/s44163-023-00097-x
[5] U. Chinta, P. Goel, A. Renuka, “Leveraging AI and Machine Learning in Salesforce for Predictive Analytics and Customer Insights”, Universal Research Reports, Volume: 10, Issue: 01, 2023, pp. 246-255. https://www.researchgate.net/publication/383597449_Leveraging_AI_and_Machine_Learning _in_Salesforce _for_Predictive_Analytics_and_Customer_Insights
[6] H. Sengar, S. Aravind, R. Kolli, O. Goel, S. Singh, P. Goel, “Ever aging AI/ML Models for Predictive Analytics in SaaS Subscription Management”, Darpan International Research Analysis, Vol. 12, Issue 3, 2024, pp. 915-928.
[7] І. Фадєєва, В. Романишин, В. Круш, “Вплив інтеграції штучного інтелекту на підвищення фінансової стійкості підприємств”, Actual Problems of Economics, # 10 (280), 2024, cc. 6-11. https://doi.org/10.32752/1993-6788-2024-1-280-6-13
[8] M. Kureljusic, E. Karger, “Forecasting in financial accounting with artificial intelligence – A systematic literature review and future research agenda”, Journal of Applied Accounting Research, Volume 25, Issue 12, 2024, pp. 81-97. https://doi.org/10.1108/JAAR-06-2022-0146
[9] N. Duc, T. Chau, P. Long, L. Nhung, B. Huy, Z. Yusof, A. Hassan, “Modernizing Taxation, Fraud Detection, and Revenue Management in Public Institutions Using AI-Driven Approaches”, QuestSquare, Volume 7, 2024, pp. 55–66. https://www.researchgate.net/publication/387756419_Modernizing_Taxation_ Fraud_Detection _and_Revenue_Management_in_Public_Institutions_Using_AI-Driven_Approaches
[10] В. Фаріон, А. Гомотюк, Р. Назар, С. Турчин, “Використання штучного інтелекту для прогнозування фінансових показників”, Економічний аналіз. Том 34. № 2. , 2024, сс. 327-337. https://doi.org/10.35774/econa2024.02.327
[11] C. Swenson, “Using Machine Deep Learning AI to Improve Forecasting of Tax Payments for Corporations”, Forecasting, Vol. 6(4), 2024, pp. 968-984. https://doi.org/10.3390/forecast6040048
[12] B. Adelakun, “AI-driven financial forecasting: innovations and implications for accounting practices”, International Journal of Advanced Economics, Volume 5, Issue 9, 2023, pp. 323-338. https://doi.org/10.51594/ijae.v5i9.1231
[13] О. Фокін, “Вплив використання штучного інтелекту на фінансовий сектор”, Академічні візії, №34, 2024. https://doi.org/10.5281/zenodo.13354429