Amazon Forecast is a fully managed deep-learning service for time-series forecasting. By providing Amazon Forecast with historical time-series data, you can predict future points in the series. Time-series forecasting is useful in multiple domains, including retail, financial planning, supply chain, and healthcare.
This repo shows how to use Amazon Forecast service to predict sales quantities in the retail industry.
Favorita is a grocery company from Ecuador and the dataset used in this example is from a Kaggle competition. More information at the competition site.
The dataset can be downloaded by logging into Kaggle and using the following link