Telco Customer Churn - [Predictive Exp.]

June 5, 2016

Report Abuse
Demonstrates setting up a predictive experiment for the Telco Customer Churn example.
This experiment builds on the [Telco Customer Churn example][1] in two parts. In this first part, we create a predictive experiment which can be deployed as a web service (operationalization) used for doing predictions in real-time (RRS) or batch mode (BES). ![enter image description here][2] After deploying a web service from this experiment, we can use the the sample code in the web service's API help page to predict churn. In the second part of this example, we add a Retraining Experiment and provide code that can retrain this model programmatically. [1]: https://gallery.cortanaintelligence.com/Experiment/Telco-Customer-Churn-5 [2]: https://operationalizatio.blob.core.windows.net/publicimages/GalleryTelcoPredictive.PNG