Creating and managing predictions
Address your customers' needs better by predicting customer behavior and business events with predictions. For example, you can determine the likelihood of a customer discontinuing a subscription (churn), or chances of successful case completion.
With Pega Platform, you can predict events in your business activity by creating predictions in Prediction Studio. Predictions are strategies driven by adaptive and predictive models.
To create a prediction, you answer several questions about what you want to predict. Based on your answers, Prediction Studio creates a self-learning adaptive model that is the basis of the prediction. You can replace this model with a different one, for example, a predictive model that you developed in a third-party machine learning platform. You can then include the prediction in your decision strategy.
For example, you can create a prediction that calculates the probability of customer churn, and then add the prediction to a next-best-action strategy. The next-best-action strategy arbitrates several actions to retain the customer, and then selects the one that the customer is most likely to accept.
Replacing a model in a prediction is possible at any time in the prediction's life cycle. As a data scientist, you can add and approve the new model in a non-production environment, and start a deployment process to migrate the new model to production.
In Prediction Studio, you can create predictions by using templates for the following use cases:
- Customer Decision Hub
- Predictions for use in decision strategies to optimize engagement with your customers. Pega Customer Decision Hub provides the most common predictions 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. For more information, see Creating predictions for customer engagement.
- Case management
- Predictions for use 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 can be used in the straight-through processing of claims. For more information, see Creating predictions for case management.
- Text analytics
- Predictions that analyze the text that comes through your channels, for example, email or chat, to predict the topic and sentiment of the message, and detect entities in the text, such as people, organizations, or ZIP codes. For more information, see Creating text predictions.
Previous topic Clearing deleted models in Prediction Studio Next topic Creating predictions for case management