The M4-Competition is the continuation of three previous ones organized by Spyros Makridakis (known as the Makridakis or M-Competitions) whose purpose was to identify the most accurate forecasting method(s) for different types of predictions. These competitions have attracted great interest in both the academic literature and among practitioners and have provided objective evidence of the most appropriate way of forecasting various variables of interest.
The purpose of the M4-Competition is to replicate the results of the previous three ones and extend them into two directions. First increasing the number of series to 100,000, and second including Machine Learning (Neural Network) forecasting method.
For more information on the datasets, visit M4 Competition site.