Pega Platform can connect to Google AI Platform models that use the following libraries:

• Scikit-learn
• TensorFlow
• XGBoost

Data scientists build models on Google AI Platform by using the supported frameworks. As a result, the inputs and outputs of the models are highly customizable. Google AI Platform relies on the data scientist who builds the model to know which features of the input data to the model are required to predict outcomes and to supply these features in the correct type and order. These features can be quite different from the features in the input data that is supplied in the training data set. Similarly, in Pega Platform, you also need to map these features to the properties that Pega Platform requires to use the model.