MACHINE METHODS OF PROBLEM-ORIENTED BUSINESS ANALYSIS OF BIG DATA OF THE VINNYTSIA REGION

Abstract

This article is devoted to the analysis of the application of machine methods for effective problem-oriented business analysis of big data in the Vinnytsia region. The main emphasis is on supply chain optimization in the context of manufacturing enterprises, which is critical for improving business efficiency and minimizing costs. Key methods and tools used to analyze and optimize business processes are covered, including machine learning for demand forecasting, time series analysis for efficient inventory management, optimization of delivery routes, and data visualization tools.

Machine learning techniques such as random forest and neural networks are used to accurately predict future demand based on analysis of historical data. This allows companies from the Vinnytsia region to more efficiently manage stocks and reduce storage costs. Time series analysis using techniques such as ARIMA helps identify seasonal fluctuations in sales, allowing inventory to be optimized in response to changes in demand. Optimization of delivery routes using optimization algorithms, such as the nearest neighbor algorithm, aims to reduce fuel costs, shorten delivery times and improve the efficiency of logistics operations.

Visualization tools such as Tableau and Power BI play an important role in providing intuitive graphical representation of complex data sets, facilitating decision making. The importance of adapting the latest technologies to local conditions and the specifics of the Vinnytsia region, as well as the integration of these technologies into the development strategy of enterprises to increase their productivity and competitiveness on the market, is emphasized. The research findings highlight the importance of integrating big data analytics and machine learning technologies to effectively solve complex business challenges.