Abstract
Abstract. Supply chain forecasting is a broad domain embracing number of topics like demand planning, pricing, supply and service prediction. It is also an integral part of many processes that those affect. This paper describes machine learning methods used in forecasting like regressions, random forest, XGBoost but also showcases the newest contributions to deep learning architectures used for forecasting like RNNs, LSTMs as well as state-of-art Transformer models created for long-term forecasting: TimeGPT and PatchTST. Paper also describes another robust approach for time series forecasting - hybrid approaches that combine both statistical and machine learning models alongside their applications.