Customer Churn Prediction

By for September 18, 2017

Report Abuse
On average, keeping existing customers is five times cheaper than the cost of recruiting new ones. As a result, marketing executives often find themselves trying to estimate the likelihood of customer churn and finding the necessary actions to minimize the churn rate. The aim of this solution is to demonstrate predictive churn analytics.
1. The **detailed documentation** for this real world scenario includes the step-by-step walkthrough at: 2. For code samples, click the "**View Project**" icon on the right and visit the project GitHub repository. 3. Key components needed to run this scenario: - An Azure account (free trials are available) - An installed copy of Azure Machine Learning Workbench following the quick start installation guide to install the program and create a workspace - For operationalization, it is best if you have Docker engine installed and running locally. If not, you can use the cluster option but be aware that running an Azure Container Service (ACS) can be expensive. - This Solution assumes that you are running Azure Machine Learning Workbench on Windows 10 with Docker engine locally installed. If you are using macOS the instruction is largely the same. - Churn Prediction code samples located in the project GitHub repository.