Abstract The paper deals with the concept of centralized demand forecasting and logistical coordination in distribution networks. The aim of the paper is to relate the results provided by the forecasting tools to the basic aspects of logistical coordination. The case of 29 distribution networks in which a logistics operator (3PL) operates and provides contract logistics services to a manufacturing company is analysed. The paper partially confirms the hypothesis of better testability of forecasts based on machine learning algorithms and artificial neural networks for demand planning by the logistics operator to the manufacturer in the framework of logistics coordination in the distribution network. These algorithms perform better for networks with high specificity of flows and food networks. Traditional algorithms, on the other hand, have their better share in creating forecasts for more standard distribution networks. Additionally, the second hypothesis regarding the positive influence of modern technological solutions (such as the use of cloud technologies, EDI and flow tracking standards) was confirmed. Additionally, a number of factors that did not have a direct impact on forecasting errors were detailed.