Amazon has developed machine-learning driven models on how to forecast demand for its services and deploy infrastructure accordingly.
Amazon Web Services has been using machine learning to anticipate demand for its services as deals work their way through the pipeline and predict how and where it should add capacity. “One of the least understood aspects of AWS is that it’s a giant logistics challenge, it’s a really hard business to operate,” accoring to AWS CEO Andy Jassy.
AWS uses a forecasting model driven by machine-learning research to make capacity decisions. For example, it can pick up signals from the process its sales teams follow (enterprise sales cycles are notoriously long) to forecast demand.
A lot of new customers like to start slow on AWS and then accelerate their usage as they see more benefits, which can lead to spikes in demand if they move faster than anticipated.
(Photo: BY/SA Fabrice Florin)