AWS Forecast Service
An AWS Forecast Service is a cloud-based forecasting service that is an AWS ML platform.
- Example(s):
- Counter-Example(s):
- See: Facebook Prophet.
References
2021
- https://aws.amazon.com/forecast/
- QUOTE: Amazon Forecast is a time-series forecasting service based on machine learning (ML) and built for business metrics analysis.
2021
- https://www.arnnet.com.au/article/690719/aws-hails-new-apac-weather-index-amazon-forecast/
- QUOTE: Amazon Web Services’ (AWS) Forecast product has added its Weather Index functionality to the Asia Pacific (APAC) region, allowing demand forecasts to utilise weather conditions.
Accessible at no additional cost, users can incorporate 14-day weather forecasts for specific locations in APAC into the predictive capabilities of Amazon Forecast.
According to AWS, the idea behind the added functionality is to estimate consumer demand patterns, product merchandising decisions, staffing requirements and energy consumption needs.
The feature works by combining multiple weather metrics from historical weather events and current forecasts at a specific location to increase the accuracy of a user’s demand forecast model.
This adds to Amazon Forecast’s overarching offering of utilising machine learning to generate demand forecasts, with the cloud giant claiming that prior machine learning experience is not required.
- QUOTE: Amazon Web Services’ (AWS) Forecast product has added its Weather Index functionality to the Asia Pacific (APAC) region, allowing demand forecasts to utilise weather conditions.
2018
- https://www.zdnet.com/article/amazon-personalize-forecast-bring-amazon-coms-ai-techniques-to-aws-customers/
- QUOTE: ... Similarly, Amazon Forecast uses time series forecasting built for Amazon.com.
"The problem in forecasting is it's not usually one or two data points that impact the forecast," Jassy said. In retail, there can be hundreds of variables to analyze, like weather, shipping times, and customer reviews.
Forecasting works very much in the same way Personalize does. A customer gives Amazon historical data such as supply chain and inventory information. They also provide all the variables that could impact their forecast. Amazon does all the work, like selecting hyper-parameters and training the models, to provide a time series forecast. .. ...
- QUOTE: ... Similarly, Amazon Forecast uses time series forecasting built for Amazon.com.