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.
Automated machine learning
No machine learning expertise is required to build an accurate time series-forecasting model that can incorporate time series data from multiple variables at once. Amazon Forecast includes AutoML capabilities that take care of the machine learning for you. Once you provide your data into Amazon S3, Amazon Forecast can automatically load and inspect the data, select the right algorithms, train a model, provide accuracy metrics, and generate forecasts.
Based on the same technology used at Amazon.com
Amazon Forecast includes algorithms that are based on over twenty years of forecasting experience and developed expertise used by Amazon.com. Amazon Forecast will automatically select the best algorithm based on your specific data sets.
Easily evaluate the accuracy of your forecasting models
Amazon Forecast provides 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 will divide the data into groups based on common attributes, like age and product type to allow you to evaluate model accuracy at a granular level. For example, a retailer can compare model accuracy for new products against products that they have been selling for more than 12 months to determine if the model needs to be updated.
Amazon Forecasts and their associated accuracy metrics are visualized in easy-to-understand graphs and tables in the service console. Once forecasts are generated, you can navigate to the relevant forecast by picking it from a list of available forecasts. For example, a specific product within your full catalog of products. Visualization allows you to quickly understand the details of each forecast and determine if adjustments are necessary.
You can schedule forecasts to run at pre-defined times to align with regular business processes like monthly financial reporting. After scheduling forecasts, you need only to provide the latest historical data in Amazon S3 on a regular cadence, and Amazon Forecast will automatically generate new forecasts as specified.
Schedule retraining of your models
You can configure Amazon Forecast to automatically retrain its models on a pre-defined schedule to better ensure that your models keep up with changes in the real world, such as rising interest rates or increased demand of a product due to evolving fashion trends. Additionally, as more historical data becomes available, Amazon Forecast may find new relationships between variables and need to adjust your forecasts to provide better accuracy. After scheduling retraining, you only need to provide the latest training data to Amazon S3 on a regular cadence. Amazon Forecast will then automatically train from the most recent time series data at the frequency you specify and update your forecasting models.
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.
Refer to developer guide for instructions on using Amazon Forecast.
Instantly get access to the AWS Free Tier.
Get started building with Amazon Forecast by signing up for preview access.