Skip to main content

Creating parameterized predictors

Introduction

Pega Customer Decision Hub™ uses Adaptive Models that use a wide range of predictors to optimize customer interactions. You can make input fields that are not directly available in the customer Data Model accessible to the models by configuring these fields as parameterized predictors. Learn how to create parameterized predictors for Expressions, offline model scores, and online model scores.

Video

Transcript

This demo shows you how to create parameterized predictors to make input fields that are not directly available in the customer Data Model accessible to Adaptive Models. We will cover three examples: Expressions, offline model scores, and online model scores.

U+ Bank is cross-selling its credit cards on the web by using Pega Customer Decision Hub™. All customer data, including financial clickstream summary attributes, such as webpage visits, is available to the Adaptive Models that determine which offer to display for a particular customer.

The first parametrized predictor is the ratio of two clickstream summary attributes that denote the number of visits to the U+ Bank Investment webpage in the last 30 days and the last 90 days. An increasing ratio might indicate growing customer interest.

The Financial Services Clickstream Data Set contains the clickstream data, which is a record of the user's activity on the website. These entries reflect the Investment webpage visits of the customer.

Record of customer actions

To populate a parameterized predictor, you configure the NBA Pre-Processing Extension Point Decision strategy that is included in a change request. The pre-processing strategy runs before the Prediction strategy so that the output of the extension strategy is available as input to the Prediction.

The first example of a parameterized predictor is an Expression that references two clickstream fields. To add a field, you add a Set Property component to the strategy and create a new property in the Strategy Results class. Set the property type to Decimal to store the ratio of customer visits to a web page in the last 30 days and in the last 90 days.

Extension strategy calculation component

This Expression returns a value of zero when the number of Investment page visits in the last 90 days is zero. Otherwise, it returns the ratio of the Investment page visits in the last 30 days to the last 90 days. A high value might indicate the increasing interest of the customer in the content of this page.

Expression Ratio 30 and 90 days

The second example of a parameterized predictor is offline model scores. A Data Set that is associated with the customer context makes the data available as a data source. Each customer can have multiple scores for different categories or different channels.

To add the model scores as potential predictors to the Adaptive Models, you add a Data Join component to the extension strategy.

Added data join component

The component joins the Offlinescores page that contains the model scores to the available data.

Data join the properties

To output only relevant scores, you specify the channel and the product category to match the Prediction.

Conditions to meet

You then create a Decimal property and map it to accommodate the model scores.

New property

The third example of a parameterized predictor is the score of a churn Prediction that runs in Customer Decision Hub. The Data Scientist team develops Predictive Models based on the latest insights and data that drive the churn Prediction.

To make the churn score available to the Adaptive Models as a parameterized predictor, add a Prediction component to the extension strategy. Reference the churn Prediction in the Customer class.

Add a Set Property component to the extension strategy to create a new property and map it to the propensity calculated by the churn Prediction.

Complete strategy

Run the strategy by using a test customer profile to verify that the strategy outputs include the real-time churn risk score, the offline product scores, and the Expression.

Next, you use Prediction Studio to map three new parameterized predictors in the Prediction. The Predict Web Propensity Prediction calculates the likelihood that a customer clicks on a web banner. Like the new properties, the system saves the Prediction results to the CDH-SR class.

The save to class

You then create three new parameterized predictors and map them to the new properties that represent customer behavior, offline scores, and online scores.

The new parameters

When you submit your work for deployment, the application saves all changes made in Predictions to a Change prediction change request.

After a review by the Team Lead, a Revision Manager deploys the changes as part of a revision.

You have reached the end of this video. You have learned:

  • How to configure the pre-processing extension strategy for parameterized predictors.
  • How to add properties as parameterized predictors to the Prediction.
  • How to submit the changes for deployment.

This Topic is available in the following Module:

If you are having problems with your training, please review the Pega Academy Support FAQs.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega Academy has detected you are using a browser which may prevent you from experiencing the site as intended. To improve your experience, please update your browser.

Close Deprecation Notice