Fighting Churn with Data

The science and strategy of customer retention

Carl Gold

• Éditeur: Manning
• Année: 2020
• ISBN:
  9781638350187
• Sujet: Ciencia de la computación
• Sous-sujet: Minería de datos

The beating heart of any product or service business is returning clients. Don't let your hard-won customers vanish, taking their money with them. In Fighting Churn with Data you'll learn powerful data-driven techniques to maximize customer retention and minimize actions that cause them to stop engaging or unsubscribe altogether. Summary
The beating heart of any product or service business is returning clients. Don't let your hard-won customers vanish, taking their money with them. In Fighting Churn with Data you'll learn powerful data-driven techniques to maximize customer retention and minimize actions that cause them to stop engaging or unsubscribe altogether. This hands-on guide is packed with techniques for converting raw data into measurable metrics, testing hypotheses, and presenting findings that are easily understandable to non-technical decision makers.Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the technology
Keeping customers active and engaged is essential for any business that relies on recurring revenue and repeat sales. Customer turnover—or "churn"—is costly, frustrating, and preventable. By applying the techniques in this book, you can identify the warning signs of churn and learn to catch customers before they leave. About the book
Fighting Churn with Data teaches developers and data scientists proven techniques for stopping churn before it happens. Packed with real-world use cases and examples, this book teaches you to convert raw data into measurable behavior metrics, calculate customer lifetime value, and improve churn forecasting with demographic data. By following Zuora Chief Data Scientist Carl Gold's methods, you'll reap the benefits of high customer retention. What's inside Calculating churn metrics
Identifying user behavior that predicts churn
Using churn reduction tactics with customer segmentation
Applying churn analysis techniques to other business areas
Using AI for accurate churn forecastingAbout the reader
For readers with basic data analysis skills, including Python and SQL. About the author
Carl Gold (PhD) is the Chief Data Scientist at Zuora, Inc., the industry-leading subscription management platform. Table of Contents: PART 1 - BUILDING YOUR ARSENAL1 The world of churn2 Measuring churn3 Measuring customers4 Observing renewal and churnPART 2 - WAGING THE WAR5 Understanding churn and behavior with metrics6 Relationships between customer behaviors7 Segmenting customers with advanced metricsPART 3 - SPECIAL WEAPONS AND TACTICS8 Forecasting churn9 Forecast accuracy and machine learning10 Churn demographics and firmographics11 Leading the fight against churn

Part 1. Building your arsenal

Before you can fight churn with data, you need to prepare the data. Knowledge is going to be your weapon in the fight against churn, but for most products and services, the raw data is useless. Although you will never stop building and honing your data, this part teaches you how to lay the foundations. The goal of this part is to show you how to accomplish a few foundational tasks: measuring churn, creating metrics for your customers, and combining your customer data into datasets for performing further analysis and sharing with your business colleagues.

Chapter 1 contains background information about the industry of online products and services. This chapter also introduces the company case studies and demonstrates the type of results the book will teach you to create. Finally, the first chapter introduces the simulated data case study that will be used in examples throughout the book.

Chapter 2 teaches the calculation of churn rates using SQL. This skill is necessary so you can measure churn properly before starting to fight it. This chapter also lays the foundation for some advanced SQL techniques later in the book.

Chapter 3 is the first chapter on the calculation of customer metrics, which is one of the main themes of the book. As you will see, carefully designed customer metrics are the main weapon you will use in the fight against churn.

Chapter 4 introduces the concept of a dataset and shows you how to create a dataset for understanding churn from your own raw data. This chapter combines the techniques from chapters 2 and 3 and is the foundation for the techniques in part 2.

1 The world of churn

What is churn? Why do we fight it? And how can data help? In short, why are you reading this book? If you are reading this book, you are probably

• A data analyst, data scientist, or machine learning engineer
• Working for an organization that offers a product or service with repeat customers or users

Or maybe you are studying to get one of those jobs or filling such a role even though it’s not your job.

Such services are often sold by subscription, but your organization does not need to sell subscriptions in order to take advantage of this book. All you need is a product with repeat customers or users and a desire to keep them coming back. This book teaches a lot of techniques related to subscriptions, but in every case, I show how the same concepts apply to retail and other nonsubscription scenarios.

To get the most out of this book, you should have a background in data analysis and programming. If that is you, then get ready for a game-changing breakthrough in the way you think about customers and data. This is not your usual book about data analysis and data science because, as you will learn, the usual approach doesn’t work for churn. But you don’t need a degree in data science to take advantage of this book: I will review enough of the basics so that anyone with a little programming experience can get great results. With that in mind, I refer to you, the reader, as a data person because this book is written from the point of view of the person who works with the data. That said, this book is packed with business insights from real-world case studies, so even if you don’t program, you can still get a lot from reading the book and then give the book to your developer when it comes time to put theory into practice. This book provides a hands-on approach to the subjects of churn and data.

If you work with an organization that offers a live service, you probably know all about churn and want to get on with the fight to prevent it. But I need to provide context for those who are just starting out; and even if you already know about churn, I need to dispel a few common misconceptions before we begin.

This chapter is organized as follows:

• Sections 1.1-1.3 provide the context for the rest of the book: what churn is, how to fight it, why fighting churn is hard, and why I have selected the topics for the book.
• Sections 1.4-1.6 make the theory concrete. I describe the business contexts where these strategies apply and what data different companies have to work with.
• Sections 1.7-1.8 bring the theory to life by looking at case studies that are featured throughout the book. By the end of the book, you will be ready to create those kinds of results for your own product or service.

1.1 Why you are reading this book

A primary goal for any service is to grow by adding customers or users through marketing and sales. (This is true for both for-profit and nonprofit enterprises.) When customers leave, it counteracts the company’s growth and can even lead to contraction.

DEFINITION Churn —When a customer quits using a service or cancels their subscription.

Most service providers focus on acquisitions. But to be successful, a service must also work to minimize churn. If churn is not addressed in an ongoing, proactive way, the product or service won’t reach its full potential.

The word churn originated with the term churn rate, which refers to the proportion of customers departing in a given period, as we will discuss in more detail later. This leads to the customer or user population changing over time, which is why the term churn makes sense. The word originally meant “to move about vigorously” (as in churning butter). In the business context, churn is now used as both a verb—“the customer is churning” or “the customer churned”—and as a noun—“the customer is a churn” or “make a report on last quarter’s churns.”

Customers not churning from a service can also be framed in a positive sense, if you prefer to see the glass as half full. In that case, people talk about customer retention.

DEFINITION Customer retention —Keeping customers using a service and renewing their subscriptions (if there are subscriptions). Customer retention is the opposite of churn.

Reducing churn is equivalent to increasing customer retention, and the terms are interchangeable to a large degree. When a goal is stated as retaining more customers longer, then in addition to saving customers who are at risk of churning, there should also be a focus on keeping customers engaged. There is even the possibility of upselling the most engaged customers more advanced versions of the service, typically for more money. Saving churns, increasing engagement, and upsells are all important goals for services with repeated customer interactions. The difference between these is a matter of focus and not a difference in the intention.

TAKEAWAY Despite the wide variety of products and services with repeat customers, there is a single set of techniques for using data to fight churn and increase engagement, retention, and upsell.

This book gives you the skills to address engagement and upsells and to fight churn effectively using data in any kind of recurring user interaction scenario.

1.1.1 The typical churn scenario

If you work in an organization that creates a subscription product, your situation probably looks something like the one shown in the top of figure 1.1. The key ingredients are as follows:

• A product or service is offered and used on a recurring basis.
• Customers interact with the product.
• Customers may have subscriptions to receive the product or service. Subscriptions often (but not always) cost money.
• Subscriptions can be ended or canceled, which is known as churn. If there are no subscriptions, a customer churns when they stop using the product.
• The timing, prices, and payments for the customers and subscriptions (if any) are captured in a database, typically a transactional database.
• When customers use or interact with the product or service, these events are often tracked and stored in a data warehouse.

In section 1.4, we’ll look at a wide variety of products that fit this description. If your scenario is not quite like this but has some of the elements, that’s fine. As described in section 1.5, the techniques in this book also apply to related situations. What is described is simply the most common situation.

Throughout the book, I interchange the terms subscriber, customer, and user. These have slightly different connotations, but in general, the same ideas apply (a subscriber has a subscription, a customer pays, and a user may not do either but you still want them coming back). The tech...