The purpose of the Phase2 project is to research and develop an advanced software solution for demand prediction (demand forecasting) of high-seasonal products, based on an innovative technological architecture that, by combining traditional statistical methods and artificial intelligence algorithms and machine learning, provides timely, high-precision and reliable predictions about the movement of demand for certain products on the market. The project will explore, identify and validate various contextual data, not yet utilized, that have a significant impact on demand and on the basis of which it will be possible to train an AI reasoning model.