Campaign Manager - Campaign Manager (Silverlight)


Predicted Next Date

Use the Predicted Next Transaction Tool to predict customers future transaction dates using product purchase cycles.

The tool uses past transaction history to predict when customers are most likely to buy again, which can then be used to establish general trends and to engineer banded columns based on purchase cycles.

Procedure

  1. Drag the tool to the workspace or select it from  Create > Engineering > Predict Next Date.
  2. Optional settings: if you want to make the column permanent so that it is saved in the database, and can be viewed and selected in the Data Explorer tab, click the Optional expand icon to display the following optional settings:
    • In the Table Column Name field, enter the name you want to use to display the column in the Data Explorer tab.
    • If you want the new column to be indexed automatically, select the Index Column check box.
  1. Other settings:
    • Target Table: This is the resolution of the calculation that is what you are performing the prediction for. This will usually be a Customer table. Drag in the required table from the Data Explorer .
    • Source: This is a filter field that specifies the transaction that you are trying to predict. It will usually be a product code or product group i.e. you will be selecting people that have purchased a particular product in the past.
    • Date : Drag in the date column that indicates when purchases have occurred in the past, for example a Transaction Date or Purchase Date column.
Note:
Only Engine columns can be used with Predictive tools. SQL column data will not be available to select in the Target Table and Date fields.

The following example is configured with LIOG3 being a product code in the Demo database:

  1. Click the Process button to run the calculation.

The results will be displayed in your document as follows:

The values helper will show future dates with the predicted number of people that will make purchases of the product on each date. This information is not that useful on its own, but can be used in conjunction with the Cycle tool to establish general trends, and to engineer banded columns based on purchase cycles.

  Online & Instructor-Led Courses | Training Videos | Webinar Recordings
© Alterian. All Rights Reserved. | Privacy Policy | Legal Notice