Deploying a Churn Prediction Model

Deploying a Churn Prediction Model

Using PMML we only need 3 nodes for the whole deployment workflow. PMML is transparent to the model type, be it a neural network or a decision tree, the PMML Predictor node understands everything.

Data & Model Reading

The previously trained model is read. It can be any kind of model saved in PMML format.

In the folder TheData/Customers the file newdata.csv simulates real life customer data. The file contains behavioral and contract data, without churn information, for one new customer only.

Apply the Model

PMML Predictor is the PMML interpreter node. Here the data and the model are brought together.

Task

Deploy a previously trained model to predict the churn for new customer data.