USING BUSINESS INTELLIGENCE TOOLS IN THE PROCESS OF FORECASTING A COMPANY'S FINANCIAL INDICATORS

Abstract

In the modern global business environment, the importance of effective management and informed strategic decision-making is becoming increasingly critical for the success of enterprises. To achieve these goals, information has become a key resource, and the use of Business Intelligence (BI) tools in the process of enterprise planning has gained significant importance. The research aims to identify and compare the practical capabilities of forecasting financial indicators using contemporary Business Intelligence tools. The formation of the net income indicator is a key component of strategic enterprise planning and requires a comprehensive analysis of internal and external factors. Various methods, such as regression analysis, time series models, and neural networks, are used for forecasting financial indicators. In this work, it is demonstrated that the selected forecasting methods have yielded positive results in identifying the dynamics of net income for TD «Kyivkhlib». The multiple linear regression model and the ARIMA model have shown similar forecasts for net income, predicting an increase by a factor of 2.03 with the first method and 2.017 with the second. A neural network also predicts an increase in net income but with a slower growth rate (2.93 times). The authors emphasize the role of Business Intelligence (BI) tools in the forecasting process of the enterprise's financial indicators. The use of BI platforms is analyzed, providing the ability to predict the company's future state, making BI an important component of strategic and economic analysis. While traditional forecasting methods based on correlation-regression analysis and time series construction are widely used, they have their limitations. They assume that past trends will remain constant in the future, but they may not always account for unforeseen events. The development of information technology has led to the use of more effective methods for intelligent data analysis in building forecasts. The use of genetic algorithms is a promising direction for modeling and forecasting financial indicators but requires the availability of appropriate data for each modeling variable. Comparing traditional forecasting methods with methods of intelligent data analysis can help understand their strengths and weaknesses and contribute to the development of hybrid forecasting tools that overcome the limitations of each method.