Advanced automated machine learning
Amazon Forecast uses machine learning (ML) to generate more accurate demand forecasts with just a few clicks, without requiring any prior ML experience. Amazon Forecast includes algorithms that are based on over twenty years of forecasting experience and developed expertise used by Amazon.com bringing the same technology used at Amazon to developers as a fully managed service, removing the need to manage resources. Amazon Forecast uses ML to learn not only the best algorithm for each item, but the best ensemble of algorithms for each item, automatically creating the best model for your data.
Explore what factors, such as price, holidays or weather, are driving your forecasts with Amazon Forecast, which provides forecast Explainability report in the form of impact scores for all your forecasts, specific time series of interest or specific time durations. Explainability provides you more insight into better managing your business operations.
Automatically include local weather information
With Weather Index, Amazon Forecast can increase your forecasting accuracy by automatically ingesting local weather information in your demand forecasts with one click and at no extra cost. Weather conditions influence consumer demand patterns, product merchandizing decisions, staffing requirements, and energy consumption needs. When you use the Weather Index, Forecast trains a model with historical weather information for the locations of your operations and uses the latest 14-day weather forecasts on items that are influenced by day-to-day variations to create more accurate demand forecasts.
Generate probabilistic forecasts
Unlike most other forecasting solutions that generate point forecasts, Amazon Forecast generates probabilistic forecasts at three different quantiles by default: 10%, 50% and 90%. In addition, you can choose any quantile between 1% and 99%, including the 'mean' forecast. This allows you to choose a forecast that suits your business needs depending on whether the cost of capital (over forecasting) or missing customer demand (under forecasting) is of importance.
Works with any historical time series data to create accurate forecasts
Amazon Forecast can use virtually any historical time series data (e.g., price, promotions, economic performance metrics) to create accurate forecasts for your business. For example, in a retail scenario, Amazon Forecast uses machine learning to process your time series data (such as price, promotions, and store traffic) and combines that with associated data (such as product features, floor placement, and store locations) to determine the complex relationships between them. By combining time series data with additional variables, Amazon Forecast can be 50% more accurate than non-machine learning forecasting tools.
Easily evaluate the accuracy of your forecasting models
Amazon Forecast provides six different comprehensive accuracy metrics to help you understand the performance of your forecasting model and compare it to previous forecasting models you’ve created that may have looked at a different set of variables or used a different period of time for the historical data. Amazon Forecast automatically splits your data into a training and testing set allowing you to download the forecasts it generates for the testing set for you to use a custom metric to evaluate the accuracy or allows you to create multiple backtest windows and visualize the metrics, helping you evaluate model accuracy over different start dates.
Integrate with your existing tools
Amazon Forecast can be easily imported into common business and supply chain applications, such as SAP and Oracle Supply Chain. This makes it easy to integrate more accurate forecasting into your existing business processes with little to no change.