Forecast Profits for Clothing Sales - sample uses a TimeSeries predictive model trained on recent purchase history of men's clothing to forecast profits for the next 4 time periods or a Streaming TimeSeries self-learning model to dynamically learn how to predict the next 4 time periods based on past purchases by women. Both take a input of sales data on a current time period to make their prediction.
Models available in \model subdirectory (catalog_timeseries.str, catalog_streaming_timeseries.str) have to be uploaded to the Watson Machine Learning instance using Dashboard (drop box). Make sure that uploaded models are named correctly (contextID).
After successful models upload deployed application should provide scoring capability as shown below.
Note that the application is fully functional only if bound to an instance of the Watson Machine Learning service, which must be done manually.