Posted on

Cluster time series data for use with Amazon Forecast


In the era of Big Data, businesses are faced with a deluge of time series data. This data is not just available in high volumes, but is also highly nuanced. Amazon Forecast Deep Learning algorithms such as DeepAR+ and CNN-QR build representations that effectively capture common trends and patterns across these numerous time series. These algorithms produce forecasts that perform better than traditional forecasting methods.
In some cases, it may be possible to further improve Amazon Forecast accuracy by training the models with similarly behaving subsets of the time series dataset. For example, consider the case of a retail chain. …

Read More