Exploring the Stock Transfer with Delivery (BME) Scenario

To learn more about the stock transfer steps, select the circles.

The Stock Transfer with Delivery (BME) scenario provides an example of a simple intelligent scenario: The embedded intelligent predictive capabilities using machine learning make it possible to predict the delivery date for a stock transport order. This information allows you to assess, based on your company's experience, whether a goods receipt can be completed successfully and on time.

You enable this predictive functionality by training and activating a predictive analytics model using the MATERIAL_OVERDUE_SIT model template. Once the predictive model is active, the system calculates the predicted delivery date and inserts this date into the Forecast Delivery Date field in the results list of the Overdue Materials - Stock in Transit app.

If required, you can also display the Predicted Deviation field. To do so, you must select this field in the view settings for the results list of the Overdue Materials - Stock in Transit app. The Predicted Deviation field shows the difference between the planned and the predicted delivery date. The Predicted Deviation information gives you an idea of whether a goods receipt can be successfully completed on time.

The figure bellow shows a screenshot of the Overdue Materials - Stock in Transit app. You can see the Forecast Delivery Date and Predicted Deviation fields. The shipping duration is displayed as a graph showing both the forecast delivery duration and the actual number of days in transit.

This intelligent scenario can be deployed in minutes with no additional configuration.

In the following interactive demo, learn how to create, train and activate a predictive model version using the MATERIAL_OVERDUE_SIT model template.