Contents
Part I: Introducing Data Science and Microsoft Azure Machine Learning
Chapter 1: Introduction to Data Science
Why Does It Matter and Why Now?
Increased Awareness of Data Mining Technologies
Faster and Cheaper Processing Power
Common Data Science Techniques
Chapter 2: Introducing Microsoft Azure Machine Learning
Hello, Machine Learning Studio!
Five Easy Steps to Creating a Training Experiment
Step 2: Preprocessing the Data
Step 4: Choosing and Applying Machine Learning Algorithms
Step 5: Predicting Over New Data
Deploying Your Model in Production
Creating a Predictive Experiment
Publishing Your Experiment as a Web Service
Accessing the Azure Machine Learning Web Service
Identifying and Removing Outliers
Building and Deploying Your First R Script
Using R for Data Preprocessing
Building and Deploying a Decision Tree Using R
Chapter 5: Integration with Python
Using Python in Azure ML Experiments
Using Python for Data Preprocessing
Handling Missing Data Using Python
Feature Selection Using Python
Running Python Code in an Azure ML Experiment
Part II: Statistical and Machine Learning Algorithms
Chapter 6: Introduction to Statistical and Machine Learning Algorithms
Part III: Practical Applications
Chapter 7: Building Customer Propensity Models
Data Acquisition and Preparation
Prioritizing Evaluation Metrics
Chapter 8: Visualizing Your Models with Power BI
Three Approaches for Visualizing with Power BI
Scoring Your Data in Azure Machine Learning and Visualizing in Excel
Scoring and Visualizing Your Data in Excel
Scoring Your Data in Azure Machine Learning and Visualizing in powerbi.com
Chapter 9: Building Churn Models
Building and Deploying a Customer Churn Model
Preparing and Understanding Data
Data Preprocessing and Feature Selection
Classification Model for Predicting Churn
Evaluating the Performance of the Customer Churn Models
Chapter 10: Customer Segmentation Models
Customer Segmentation Models in a Nutshell
Building and Deploying Your First K-Means Clustering Model
Identifying the Right Features
Properties of K-Means Clustering
Customer Segmentation of Wholesale Customers
Loading the Data from the UCI Machine Learning Repository
Using K-Means Clustering for Wholesale Customer Segmentation
Cluster Assignment for New Data
Chapter 11: Building Predictive Maintenance Models
Predictive Maintenance Scenarios
Data Acquisition and Preparation
Techniques for Improving the Model
Creating a Predictive Experiment
Publishing Your Experiment as a Web Service
Chapter 12: Recommendation Systems
Recommendation Systems Approaches and Scenarios
Data Acquisition and Preparation
Chapter 13: Consuming and Publishing Models on Azure Marketplace
What Are Machine Learning APIs?
How to Use an API from Azure Marketplace
Publishing Your Own Models in Azure Marketplace
Creating and Publishing a Web Service for Your Machine Learning Model
Publishing Your Experiment as a Web Service
Obtaining the API Key and the Details of the OData Endpoint
Publishing Your Model as an API in Azure Marketplace
What Is the Cortana Analytics Suite?