Predictive analytics uses past data to find patterns and uses those patterns to predict what will likely happen in the future.

A person can create predictive analysis models in Pega Prediction Studio.

There are three options for creating predictive models:

1. Using Pega Machine Learning. You can build a new predictive model using the proprietary Pega machine learning wizard. Import a file containing historical data and build the model in Prediction Studio. This model can then be used in decision strategies. When the decision strategies execute, the models are executed inside the Pega platform.

Building models with Pega machine learning 

The model build itself consists of 5 steps: Data preparation, data analysis, model development, model analysis, and model selection. 

 -Create a predictive model 

Intelligence > Prediction Studio > Models > New >  Predictive Model 

In the New predictive model dialog box, in the Name field 

In the Category list, select Retention. 

In the Template list, select Churn Modeling. 

Click Start. 

 Prepare the data 

In the Source selection section, click Choose File > Check the data, and then click Next. 

In the Outcome definition section, in the Model type list, select  

In the Outcome field to predict, select Segment. 

In the Outcome category list for churned, select  

In the Outcome category list for loyal, select  

– Analyze the data 

Data analysis > Click New virtual field > write function > Click Save-close. 

-Develop predictive models 

In the Model development section, select Use best of each group. 

Model Creation > Create Model > Decision Tree > Create Model 

Select ID3 >Click Create >Examine the model created > Click Submit to save the model. 

 – Analyze the models 

Ensure that the check boxes next to all models are selected. 

Click Analyze charts. 

Select the Discrimination tab and examine the results. 


2.Importing Models. You can import PMML models that were built in third-party tools like R or Python. Similarly, you can import model files that have been generated in is a modelling platform, and the procedure for using the model is similar to PMML. 

       *PMML is an XML-based standard that is designed to facilitate the exchange of models between applications. 

– Import an H2O model 

Intelligence > Prediction Studio > Models 
In the top right, click New> Predictive Model 

In the New predictive model dialog box, enter the following information: 

  • Name: ….. 
  • Click Import model. 
  • Click Choose File, and then select the ……. model file. 

Next> Enter the Expected performance > Click Import. 

*On the Mapping tab, verify that all predictors of the model are correctly mapped to the fields of the data model. 

3.Referencing External Models. In the Pega platform, you can reference a model  on an external platform like GoogleML or Amazon SageMaker. In this case, the  model itself is executed on the third-party platform, and the outcome is sent back to Pega. 

         *Like with the Google AI Platform, you can connect to AWS SageMaker and  run your model remotely. 

When the decision strategies using predictive models execute, the models are executed inside Pega or externally by Google ML and the Amazon SageMaker platform. 

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.