Swrve is excited to officially introduce our churn propensity capability, leveraging machine learning models that identify changes in customer behaviors to determine the churn propensity of each customer before they leave. We are excited to help brands deploy re-engagement strategies that reduce churn and, as a result, increase revenue.

So, what does this mean for brands? Well, being able to accurately predict the future is something that has usually only been done by superhumans, like Destiny from X-Men, or Greek deities, like the Oracle of Delphi. However, today’s combination of technological innovation and data analysis has added another to this category: the common marketer. And fortunately for us, this is firmly rooted in reality through Swrve.

Being able to predict churn is exceedingly valuable to brands. Knowing which users are at most risk of abandoning your app enables you to take action to mitigate it. A 1% reduction in churn typically equals 5% increase in customer lifetime value. Plus the fact that it costs 5x more to acquire a new customer than it does to retain an existing one means this is something that all brands should be taking seriously.

So, how does it work? Well, Swrve generates a score for each user who has not already churned from your app on a scale of 0 to 100 indicating how likely they are to churn; that is, how likely they are to stop using your app forever. A score of 0 indicates no predicted chance to churn, and 100 indicates predicted certainty of churn. You can then create retention campaigns and deliver them to users based on their individual propensity scores.

Swrve is in a particularly good position to help because we have years of experience and expertise helping leading brands reduce churn using data from a huge variety of industries and apps. And so we have a lot of data (over 14 billion data points streamed daily, in real time, to be exact). We learn constantly from this data, and periodically train new models to allow us to continually infer accurate propensities. And, put simply, the proof is in the data. Furthermore, Swrve has developed churn propensity scoring using best-in-class algorithms and models that are built on research that goes back decades, and then designed around the Swrve ecosystem.

In essence this de-risks your marketing campaigns, with the perfect blend of churn prediction and audience throttling.

We also realize that every app is different, and this has to be taken into careful consideration. Take for example an airline app, which the average traveler probably only uses a handful of times a year, compared to a freemium game, which is potentially used every day. The warning signs of churn are quite different, and so are the methods of retention. And that’s without taking into consideration that each brand has customers that have different patterns of usage. Within a retail app like Amazon, there are everyday shoppers of small items, and shoppers who only spend once a month on large items. Each type of customer would require a different type of retention campaign for it to be truly effective.

Swrve understands these nuances and complexities, and that’s why we’ve built the most flexible implementation of propensity scoring on the market. Our enterprise-grade churn model is designed to account for the nature of your app, your industry, and the range of customer profiles you market to.

The flexibility comes in a large part from being able to set distinct thresholds for scores so that you can ensure the right people receive the right retention campaigns. Setting a threshold high (e.g. 95) will target a fewer amount of users, but these will be only the ones who are the most likely to churn. This would be effective for exclusive offers that you don’t want a large number of your user base taking advantage of (e.g. 6 months free subscription to your streaming service). In essence this de-risks your marketing campaigns, with the perfect blend of churn prediction and audience throttling.

Churn propensity is a key feature of real-time relevance in Swrve. For more information on how this tool can be used to help your team meet its specific retention goals, contact us here.