28 September 2025 in Фінансовий простір
The article explores the possibilities of using Big Data and artificial intelligence technologies to forecast demand for postal and logistics services in Ukraine in conditions of increased turbulence caused by military operations, instability of market processes, and dynamic changes in demand. Key data sources are considered, as well as methods for their processing and analysis to build more accurate and adaptive predictive models. The study paid particular attention to the analysis of modern data mining tools, in particular clustering using the DBSCAN method and time series forecasting using Long Short-Term Memory (LSTM), which are currently the most effective for time series forecasting. A comparative analysis of traditional forecasting methods and models built using artificial intelligence and Big Data technologies was conducted to identify the forecasting method with the lowest percentage of forecast error. The study is based on an analysis of modern scientific publications on the topics of Big Data, machine learning, and logistics.