Skip to main content
Verify the version tags to ensure you are consuming the intended content or, complete the latest version.

Predictive models drive predictions

Introduction

Learn how to better address your customers' needs by predicting customer behavior and business events with predictions. For example, you can determine the likelihood of customer churn or chances of successful case completion.

Predictions combine predictive analytics and best practices in data science.

Video

Transcript

This video shows you how predictions can predict events in a business activity.

You can create and use predictions for several use cases.

Pega Customer Decision Hub™ predictions are used in decision strategies to optimize engagement with customers.

The most common predictions are provided out of the box. You can use the default predictions or create your own.

For example, you can use predictions to predict whether customers are likely to accept your offer or cancel a subscription.

Customer Decision Hub

Case management predictions are used in case automation to route cases or prioritize work.

For example, you can create a prediction that predicts whether a case is likely to be completed successfully,or the probability that a claim is fraudulent, which might be useful in straight-through processing of claims with a low score.

Case management

Text analytics predictions analyze the text that comes through your channels, such as email or chat, to predict the topic or sentiment of the text.

Text analytics

Predictions are created and managed in Prediction Studio, the dedicated workspace for data scientists.

Prediction Studio

A next-best-action designer can include the predictions in decision strategies in Customer Decision Hub, to better adjust to customer needs and achieve business goals at the same time.

This handover of predictions from the data scientist to the next-best-action designer contributes to a separation of concerns.

Predictions combine predictive analytics and best practices in data science.

A predictive model drives a prediction. A data scientist can replace the predictive model at any time. However, the prediction always predicts the same outcome.

For example, you can create a new Customer Decision Hub prediction that calculates the likelihood that a customer might end a subscription soon.

To drive the prediction, a data scientist creates a predictive churn model on a platform of choice.

Prediction Studio supports the PMML and H2O model file formats. It can connect to machine learning services like Google ML and Amazon SageMaker.

You also have the option to use Pega machine learning.

Predictive models

One of the predictions that is shipped with Customer Decision Hub, Predict Web Propensity, calculates the likelihood that a customer clicks on a web banner.

Customer Decision Hub decides which banner to show based on the calculated propensity and weighting in business requirements and context.

Premier Rewards Card

In this case, the Premier Rewards card has a propensity of 0.8, and it is ranked as the next best action.

The Predict Web Propensity prediction is driven by an adaptive model that learns from each customer interaction.

Best practices in data science include the use of a control group. Customers in the control group are shown a random banner instead of one based on the calculated propensity.

Comparing the success rate in the control group and the test group measures lift, which is the boost in success rate that the prediction generates. Lift is an important business metric.

When the lift drops significantly over time, Prediction Studio notifies the data scientist.

Predict Web Propensity

The response timeout is built into predictions. When the timeout expires, NoResponse is automatically recorded as the outcome of the interaction.

Response timeout

You have reached the end of this video. What did it show you?

  • How predictions can predict events in the business activity
  • How a prediction uses a control group to measure the boost in success rate that is generated by the prediction
  • How NoResponse is automatically recorded as the outcome of the interaction when the response timeout expires

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