AWS has announced the general availability of Amazon Forecast, a fully managed service that uses machine learning intended to deliver highly accurate forecasts. It’s actually based on the same technology that powers Amazon.com.
Amazon uses forecasting to make sure that the right product is in the right place at the right time by predicting demand for hundreds of millions of products every day. Amazon Forecast uses this same technology to build precise forecasts for virtually any business condition, including product demand and sales, infrastructure requirements, energy needs, and staffing levels. AWS claims these predictions to be up to 50% more accurate than traditional methods.
Using machine learning, Amazon Forecast would automatically discover how variables such as product features, seasonality, and store locations affect each other. These complex relationships can be difficult to spot using traditional forecasting methods, stated AWS. Amazon Forecast uses the machine learning developed at Amazon to quickly recognize complex patterns to improve forecast accuracy. Amazon Forecast automatically sets up a data pipeline, ingests data, trains a model, provides accuracy metrics, and performs forecasts.
Developers do not need to have any expertise in machine learning to start using Amazon Forecast. They can use the Amazon Forecast Application Programming Interface (API) or console to build custom machine learning models “in less than five API calls or clicks.” With Amazon Forecast, customers would be able to achieve accuracy levels that used to take months of engineering in as little as a few hours.
Amazon Forecast is available today in US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Tokyo), Asia Pacific (Singapore), and EU (Ireland) with more availability zones coming soon.
Forecast Accuracy: Implications
By examining historical trends, organizations can make a call on what might happen and when. They can build that into their future plans for everything from product demand to inventory to staffing. Given the consequences of forecasting, accuracy would really matter. If a forecast is too high, organizations will over-invest in products and staff, which ends up as wasted investment, and if the forecast is too low, they will under-invest, which could lead to a shortfall in raw materials and inventory; creating a poor customer experience.
Amazon has a wealth of knowledge in building accurate forecasts using machine learning from over 20 years of experience operating the world’s largest ecommerce business. Delivering billions of packages per year, with a multitude of delivery options in more than ten thousand zip codes, Amazon has developed advanced forecasting capabilities that incorporate the full product history and overlay context from related business activities, such as promotions and pricing changes. Due to this diverse and large-scale forecasting experience at Amazon, customers have asked AWS to share this knowledge with them to help make their own forecasts more accurate.
“Amazon Forecast now offers the forecasting expertise from Amazon’s first 25 years of building the world’s largest ecommerce business in a managed service for any company to leverage,” said Swami Sivasubramanian, Vice President, Amazon Machine Learning. “We’ve built sophisticated, machine learning forecasting algorithms over many years that our customers can now use in Amazon Forecast without having to know anything about machine learning themselves. We can’t wait to see how our customers use the service to reduce operating expenses and inefficiencies, ensure higher resource and product availability, deliver products faster, and lower costs to delight their customers.”