LinkedIn
Copied!

Table of Contents

Creating predictions with historical data

Predict business events and customer behavior by creating predictions that learn based on the outcomes of previous and incoming customer interactions.

Import your historical data into a data set. For more information, see Importing data into a data set.
Ensure that the data set contains a pyOutcome property for the outcome of each customer interaction, as well as properties that describe the context of each interaction, for example, pyIssue, pyGroup, pyName, pyDirection, and pyChannel.
  1. In the navigation pane of Prediction Studio, click Predictions.

  2. In the header of the Predictions work area, click New.

  3. In the New prediction window, specify what you want to predict:

    To predict whether a customer is likely to accept an offer, select the following settings:
    1. In the Subject of the prediction list, select Customer.
    2. In the Outcome of the prediction list, select Accept.

    To predict whether a customer that is likely to click a web banner is also likely to accept the corresponding offer and convert, select the following settings:

    1. In the Subject of the prediction list, select Customer.
    2. In the Outcome of the prediction list, select Click + Conversion.
      This type of prediction requires long-term feedback. For more information, see Delayed learning of adaptive models.
  4. Start the Prediction wizard by clicking Start.

  5. In the Select data wizard step, click I have historical data, and then select the data set that you create in the Before you begin section.

    If you want to create a prediction without historical data, see Creating predictions without historical data.
  6. Confirm your settings by clicking Next.

  7. In the Prediction configuration wizard step, review the response labels for the prediction, and then click Next.

  8. In the Select predictors wizard step, select the fields that you want to use as input for the prediction.

    To increase the accuracy of your prediction, select a wide range of fields to use as predictors. Do not include fields that are not suitable as predictors, for example, the Identifier and Date Time fields. For more information, see Best practices for adaptive and predictive model predictors.
  9. Confirm your choice of predictors by clicking Next.

  10. In the Review prediction wizard step, review your prediction settings, and then complete the model creation process by clicking Create.

    When you create predictions, Prediction Studio creates adaptive models as the basis of the predictions. For more information about adaptive models, see Adaptive analytics.
  11. To change the prediction settings at this stage, in the Prediction workspace, click Configure, and then make your changes.

  12. Click Save.

    The prediction is now available in the Predictions workspace.
  13. If you are using parameterized predictors, add them to the adaptive model that is the basis of the prediction.

    For more information, see Adding parameterized predictors.
    To open the adaptive model that is the basis of the prediction, in the Prediction workspace, on the Models tab, click the name of the corresponding model.
  14. Optional:

    To customize your prediction, for example, by changing the control group settings or by configuring the response time-out, see Customizing predictions.

Include the prediction in your application, for example, as part of a decision strategy.

For more information, see Defining a Prediction shape.

Did you find this content helpful?

Have a question? Get answers now.

Visit the Collaboration Center to ask questions, engage in discussions, share ideas, and help others.