Застосування штучного інтелекту (ШІ) та машинного навчання в прогнозуванні попиту в логістичній та операційній діяльності підприємства

Abstract

The thesis examines modern approaches to demand forecasting in the logistics and operational activities of enterprises under conditions of digital transformation and an unstable market environment. The limitations of traditional statistical forecasting methods are substantiated, and the feasibility of using artificial intelligence and machine learning tools to improve the accuracy of managerial decision-making is proven. The study analyzes the application possibilities of ARIMA, Prophet, and XGBoost algorithms, as well as deep learning models such as LSTM, GRU, and hybrid approaches in operational planning processes.