Improving Forecast Accuracy with Machine Learning will be retired on December 31, 2023. After that time, all existing deployments will continue to work and customers will retain full control of their environments and data, however, the solution will no longer be supported or maintained.
If you are considering a new deployment, please refer to the Automate the deployment of an Amazon Forecast time-series forecasting model blog post.
The Improving Forecast Accuracy with Machine Learning solution automatically produces forecasts and generates visualization dashboards for Amazon QuickSight or Amazon SageMaker Jupyter Notebooks—providing a quick, easy, drag-and-drop interface that displays time series input and forecasted output. Forecasting can be applied to predict retail inventory demand, supply-chain planning, workforce status, web traffic forecasting, and more.
Forecasts can be compared across dimensions (for example, retail store location) or item-level metadata (for example, product brand, size, and color). You can use this data for the following:
- Optimize existing forecasts - Save time and retain compatibility with your legacy tools, or gain insight into over- and under-provisioning, with the median (P50) forecast.
- Meet variable customer demand - Provide high levels of customer satisfaction with the P90 forecast, where the true value is expected to be lower than the predicted value 90% of the time.
- Avoid over-provisioning - Save on costs and avoid over-provisioning with the P10 forecast, where the true future demand value is expected to be lower than the predicted value only 10% of the time.
Streamline the process of ingesting, modeling, and forecasting multiple experiments through the automation of Amazon Forecast.
Provide a secure one-click deployment using an AWS CloudFormation template developed with the AWS Well-Architected Framework methodologies.
Easily monitor forecasts by emailing users when successes and failures occur.
Facilitate collaboration and experimentation by combining your input data and forecast output in an Amazon QuickSight Analysis or Jupyter Notebook.
The AWS CloudFormation template deploys the resources required to automate your Amazon Forecast usage and deployments. Based on the capabilities of the solution, the architecture is divided into three parts: data preparation, forecasting, and data visualization. The template includes the following components:
An Amazon Simple Storage Service (Amazon S3) bucket for Amazon Forecast configuration where you specify configuration settings for your dataset groups, dataset predictors, and forecasts, as well as the datasets themselves.
An Amazon S3 event notification that invokes when new datasets are uploaded to the related Amazon S3 bucket.
An Amazon Simple Notification Service (Amazon SNS) email subscription that notifies administrative users with the results of the AWS Step Functions.
An Amazon SageMaker notebook instance that data scientists and developers can use to prepare and process data, and evaluate forecast output.
An AWS Glue job combines raw forecast input data, metadata, predictor backtest exports, and forecast exports into an aggregated view of your forecasts.
Amazon QuickSight analyses can be created on a per-forecast basis to provide users with forecast output visualization across hierarchies and categories of forecasted items, as well as item level accuracy metrics. Dashboards can be created from these analyses and shared within your organization.
In this blog post, we will show you how to build a reliable retail forecasting system using Amazon Forecast and an AWS-vetted solution called Improving Forecast Accuracy with Machine Learning.
Learn how the Improving Forecast Accuracy with Machine Learning Solution simplifies short-term electric load forecasting for power and utilities to improve grid reliability.
This courses clarifies both the machine learning stack and the terms and processes that will help you build a good foundation in machine learning.
After taking this set of courses, you’ll understand how Artificial Intelligence (AI) led to Machine Learning (ML), which then led to Deep Learning (DL).