Azure ML Churn Tutorial

December 11, 2015

Report Abuse
The purpose of this lab is to introduce you to hosting machine learning models in Microsoft Azure cloud, full documentation at
The purpose of this lab is to introduce you to **hosting machine learning models** in Microsoft Azure cloud, including basic design, experimentation and development tasks. Full documentation should be found here before starting **[ ].** In the lab, we will cover Azure ML Studio, a fully managed machine learning platform that allows you to perform predictive analytics. Azure ML Studio is a user facing service that empowers data scientists and domain specialists to offer customers end-to-end solutions by significantly reducing the complexity to build predictive models. Azure ML provides an interactive and easy to use web-based interface with a drag-and-drop authoring model and a catalogue of modules that encapsulate functionality for the end-to-end model construction workflow. Azure Machine Learning is part of the Cortana Analytics Suite, a fully managed big data and advanced analytics suite that enables you to transform your data into intelligent action. As a part of the lab, you will be creating **two different models based on the dataset called Churn**. The dataset consists of records belonging to 4667 customers of a fictitious telecom service provider. The columns of the dataset hold information such as the length of customer account, total day, and night, evening and international minutes used. The first model you will create is called churn analysis known as customer attrition which is the problem of identifying the customers who are likely to leave a service or a business. The goal of the analysis is to contact these high risk individuals and take necessary actions such as providing special offers and discounts to prevent them from leaving the business. You will model the problem using the binary classification technique. Additionally, sections are provided in the documentation to create a web service for the model and visualizing the classification results using *Power BI desktop*. The second model you will create is a **segmentation model** where the objective is to find natural clusters of customers within the data sets who have similar characteristics. This is also extremely beneficial to understand the customer base for targeted marketing applications where the goal is to target the right individuals in order to grow the business. Lab content created by **Fidan Boylu Uz**, with contributions from **Danielle Dean** and **Muxi Li**. Created by Microsoft Employees.