Most of the media and e-commerce Chief Data Officers I talk to on a daily basis dream of an active collaboration between their Marketing and Data Science teams. To realize this goal, we suggest setting a use case that promotes cooperation between colleagues with different skill-sets. One of our favorite cross-team approaches is to practice a use case involving Churn Analytics.
According to Wikipedia, the definition of churn is:
"Churn rate (sometimes called attrition rate), in its broadest sense, is a measure of the number of individuals or items moving out of a collective group over a specific period of time."
Keep Your Fishes Home
Churn Detection Depends on the Subscription Model
The first step in a churn-based data science project is to define the model used by an organization; typically, there are two varieties: subscription and non-subscription. Some examples of subscription types can be found in our customers:
- Subscription Model
- Non-subscription Model
Determining whether or a not a customer will become a churner (i.e., no longer remain a customer) is fairly straightforward in subscription models, but a bit more challenging in non-subscription models. In subscription models, a customer churns when they request cancellation of their subscription. In non-subscription models, however, you need to analyze your customer’s behavioral tendencies in order to identify potential churn (e.g., the amount of time since he last used the company’s services/products). The goal is to then determine the specific point when your customer will no longer use your services or products.
Dealing with Churn over Multiple Time Spans
Churn projects are typically launched when the customer acquisition rate diminishes. For most companies, the customer acquisition cost (cost of acquiring a new customer) is higher than the cost of retaining an existing customer… sometimes by as much as 15 times more expensive (Winning New Business in Construction by Terry Gillen, 2005). Therefore, the challenge of implementing a successful churn project is to increase customer loyalty and, consequently, increase company revenue.
How Can Different Modelling Approaches Solve Churn Issues?
There are two complementary modeling approaches used to predict churn:
- Machine Learning Model (short term action): Develop a Machine Learning model to analyze performances that will enable short-term actions. Based on the outcome of this analysis, our clients are able to undertake one-shot actions to reduce churn;
- Analytical Model (long term study): Develop a model to understand the reasons causing the churn. This deeper knowledge enables our clients to attack the root of the problem and to understand how to reduce churn.
In both cases, it is crucial to connect your models to marketing-driven actions in order to attain churn reduction. Some examples of short and long-term actions include:
- Short-term actions:
- Special offers (e.g., calls, e-mails, push notifications, free in-game money, discount coupons, etc.);
- Feedback loop to control efficiency;
- Model the probability of churn due to the offer.
- Long-term actions:
- Purchase funnel optimization;
- Analyze whether or not the offer is correctly adapted to the customer base.
Only a combined approach of mixing short-term actions (in order to retain potential churners) with longer-term approaches will have an effective and sustainable impact on churn reduction.
Using Data Science to Model Churn
Churn analytics projects can be addressed by Data Science and Marketing teams thanks to Machine Learning modeling (classification) with a defined target. The target is known in subscription business models while it needs to be defined in non-subscription scenarios.
Step 1: Create a Churner Profile and Identify Churner Behavior
Segmentation: Segment your customers based on their behavior and address the question, “Which customers do we care about?” Only the best? The most valuable? Regardless of the answer, a churn reduction campaign should be targeted toward a well-defined customer segment;
Compare to Control Population: By understanding the extremes of churners, new customer classes can be created and refined. On one extreme there are customers who interacted with the product at least once, but no longer visited afterwards. The other extreme includes customers who make frequent uses or purchases and are heavily engaged with the product. In this context, the definition of a “new customer” can be formulated along with an understanding of customer groupings;
What Makes your Churner Different?: Data collected from the above analysis, when subjected to Machine Learning modelling, enables your company to discover differential patterns among churners and identify what makes your churners different from others.
Step 2: Implement a Churn Scoring Mechanism
Implementing a churn scoring mechanism relies on a pair of processes:
- Find Relevant Features: Customer features, such as social information and behavior-based actions, are used to paint a picture of who your customers are. Start the churn scoring process by finding the customer features that are the most relevant to your churn calculations;
- Compute a Churn Score: Churn score computation combines all relevant customer features to determine exactly how likely specific customers are to abandon your product/service. At this point, machine learning technology takes over — predictive algorithms are fed into Dataiku DSS and the best one is selected. It is then deployed to calculate a churn score.
Yes, the way you do marketing is about to change.
Implementing the Churn Scoring Mechanism
The process of churner identification and behavioral analysis involves expertise from both Data Scientists and Marketing Specialists: one party understands the customers whilst the other can measure & analyze behavior. At the end of this process, it is time to apply the information learned to the company’s loyalty program. The output of a churn project is a dataset (Excel or CSV file, or a table stored in your customer database) that contains the customer ID and an associated churn score. This churn score indicates the probability of the customer abandoning your product or service. With this score, the Data Science and Marketing teams can build business rules that define customer segments.
Churn Scoring Applied
Churn scoring is used to assign a score to customers that conveys the potential loyalty of the customer. Churn scores enable Data Science and Marketing to build business rules together in order to define customer segments. For example, a churn scoring mechanism would enable your company to creatively segment customers — sample types and potential actions include:
- Churners: Sending them a special offer via e-mail;
- Loyal Customers: Take no action;
- Potential Churners (we want to keep): Sending them a special offer via e-mail;
- Customer Ambivalence (unsure whether to keep or not): Sending them a Greetings e-mail without an offer.
In order to achieve optimal results, the actions need to be customized based on your business requirements and your knowledge of customer behavior & expectations. Actual deployment of your churn scoring methods can be done by feeding e-mail marketing automation tools and push engines for in-app notifications. Want to fight against customer churn, but don’t know how to begin your project? Have a look at our Whitepaper “The Modern Marketer’s guide” to find out how to deploy your marketing project.