Maintained with ☕️ by
IcePanel logo

Amazon Forecast now supports what-if analyses

Share

Services

Now with [Amazon Forecast](https://aws.amazon.com/forecast/), you can seamlessly conduct [what-if analyses](https://aws.amazon.com/blogs/machine-learning/conduct-what-if-analyses-with-amazon-forecast-up-to-80-faster-than-before/) to quantify the potential impact of business scenarios on your demand forecasts. Amazon Forecast is a fully managed service that uses machine learning (ML) algorithms to deliver highly accurate time series forecasts. Simulating hypothetical scenarios through what-if analyses is a powerful business tool to [stress test your planning assumptions](https://github.com/aws-samples/amazon-forecast-samples/blob/main/notebooks/advanced/WhatIf%5FAnalysis/WhatIf%5FAnalysis.ipynb) by capturing possible outcomes. It is a common practice to assess the impact of business decisions on revenue or profitability, quantify the risk associated with market trends, or evaluate how to respond to logistics and workforce changes to meet customer demand. With this launch, we combine Amazon Forecasts’ predictive power with a seamless experience to help you answer what-if questions and quantify the impact of hypothetical scenarios on forecasts. Now, you can [define a scenario](https://docs.aws.amazon.com/forecast/latest/dg/what-if.html) by transforming your initial dataset through simple operations such as multiplying price for Product A by 90% or decreasing the price for Product B by $10\. These transformations can also be combined with conditions to control the parameters that the scenario applies in (e.g. reducing product A’s price in one location only). You can also view forecast predictions across all scenarios in the same graph or bulk export the data for offline review. This feature is available in all Regions where Forecast is publicly available. For more information about Region availability, see [AWS Regional Services](/about-aws/global-infrastructure/regional-product-services/).