One of the most challenging machine learning problems is predicting some output based on the history of its previous values. The complexity of the problem multiplies as new features and constraints are added to analysis. Thus, in time series analysis it is not always enough to use previous values only, there often are many features that could impact on the output which should be predicted. There are numerous models and algorithms developed for this kind of problem. In this article, and series of articles that follows, several models, such as ARIMA, VAR and  Facebook Prophet, will be introduced and finally …