Importing predictive models

During a Pega Decision Management implementation project, you may discover that the company already uses predictive models. These assets can be reused in Pega Decision Management to help make customer predictions.

This demo will show you how to import third-party predictive models into Prediction Studio and use them natively in Next-Best-Action strategies.

Prediction Studio supports two external model formats. First, you can import models in the Predictive Model Markup Language (PMML) format. PMML is an XML-based language aimed at easily sharing predictive models between applications. It is the de facto standard for representing not only predictive models, but also data, pre- and post-processing.

Additionally, you can import models built with H20.ai, an open source machine learning and predictive analytics platform that allows you to build machine learning models on big data. The processes for importing PMML and H20 models are identical and start with creating a new predictive model strategy component.

Prediction Studio offers three options for creating a predictive model: using Pega machine learning, importing a previously built model, or using an external model.

To leverage an existing model file, select the Import model option. Upload the PMML or H2O model file. The default context of the model is the Customer class, where the customer data model properties are stored. You can change this class if required.

In the Outcome definition dialog box, you define which probability you would like to predict and the expected performance of the model, which is used as a benchmark when monitoring the model.

Import the model and, on the Mapping tab, make sure that all predictors are mapped to fields in the data model. Missing fields can be created, but this should be discussed with the system architect beforehand.

After the model is saved, you can test it for a single customer or run it for a batch of customers.

When you test the model for a single customer, you can use a data transform as input data. When customer Troy is used as the data source, the model predicts that he is likely to churn. The model also outputs his propensity to churn, which is, in this case, 93.42%.

In contrast, the model predicts that customer Barbara is likely to remain loyal, with a low propensity to churn of 35.83%.

You can also run the model on a batch of customers. When the model is run for a larger input data set, the output shows the number of customers that are classified as either likely to remain loyal or likely to churn in the near term.

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

• How to import third-party predictive models into Prediction Studio.
• How to test the model for a single customer.
• How to run the model for a batch of customers.