Demand forecasting: AI-based, statistical and hybrid models vs practice-based models - the case of SMEs and large enterprises

Demand forecasting is one of the biggest challenges post-pandemic logistics. It appears that logistics management based on demand prediction can be a suitable alternative to just-in-time concept. This study aims identify effectiveness AI-based and statistical models versus practice-based for SMEs large enterprises in practice. The compares Prophet model with models, artificial intelligence, hybrid developed academic environment. Since most ones were within last ten years, also answers question whether new have better accuracy than older ones. are evaluated using multicriteria approach different weight settings enterprises. results show has higher other time series. At same time, slightly less computationally demanding neural networks. On hand, evaluation while methods more SMEs, prophet method very effective case sufficient computing power trained predictive analysts.