Member-only story
How to Effectively Forecast Time Series with Amazon's New Time Series Forecasting Model
Learn about the new Amazon time series model, which you can use to forecast energy usage, traffic congestion, and weather.
I will discuss Amazon's new Chronos time series forecasting model [1]. The model can be used for a variety of time series forecasting tasks, such as predicting energy usage, traffic/congestion forecasting, or weather prediction. This makes it both flexible and powerful. I will discuss the model's performance, strengths and weaknesses, and how you can implement and run it locally.
Motivation
The motivation for this article is to follow up on the latest models within machine learning. I learned about this model from looking at PapersWithCode, one of the sources I consistently check to keep up with the latest trends in machine learning. Whenever I find something interesting, I like implementing it and getting a feel for the model and its performance. This article will discuss how you can use this model yourself, which tasks you can apply the model to, and my thoughts on the performance of the model.
After running the model, you will be able to make forecasts for the model, like in the image you see below:
