We have so far been building our models by hand. This has given us granular control over what is happening, but it can also be a lengthy process. Thus, it’s time to explore some tools for automatic time series forecasting. These tools are widely used in the industry, as they are easy to use and enable quick experimentation. They also implement state-of-the-art models, making them easily accessible to any data scientist.
Here we’ll explore the ecosystem of automatic forecasting tools and focus on Prophet, as it is one of the most popular libraries for automatic forecasting, and more recent libraries model their syntax on that of Prophet. This means that if you know how to work with Prophet, it is easy to work with another tool.