They might sound complicated, but propensity models are simply data equations that can quantify the chances of churn, based on past data.

In an INMA Digital Subscriptions Blog, Economic Times group product manager Utkarsh Arora explains just how it’s done.

“In the case of churn, a propensity model ingests past behavioural data, transactional records and other profiling data about each user, applies logic and algorithms, and then calculates a score against each user signifying the chances of churning by the end of their membership cycle,” he says.

Calculating churn risk scores across a user base enables teams to take targeted actions to reduce churn. “Churn rate is a lag metric, and if reporting business metrics is your only goal, then it’s absolutely fine to refer back to the time series of monthly churn data and make predictions for the year to come.”

To take effective action to prevent readers from churning, you need to use data analytics to understand which readers have the highest risk of churning, what common traits identify them through behaviour, work profile, demographics, satisfaction surveys and activation of key sticky habits.

In terms of behaviour on the platform, how do these users differ from the low-risk groups; at what stage are readers transitioned from being low-risk to high-risk, and what actions – or lack of actions – lead to this.

“This mindset is a good starting point when thinking about reducing churn,” he says. “The answers to the above questions will unfold the targeted actions you should take for different cohorts of readers.”

Among key variables that could have strong correlation with churn, are the number of days they were active in the first and last months of membership, the volume consumed in a session, strong engagement with at least two sticky or core topics, and a high degree of participation in virtual events. Also track the typical time of the day for consuming content, average session duration, and engagement levels during a free trial.

Variables for a profile might include the plan duration and net price paid, reasons for signing up, years of work experience, and job level.

“Not everyone may have such comprehensive data available, so to get started, I recommend focussing only on basic engagement data and running simple analyses that help you understand what’s driving renewals,” he says.

To analyse churned users who renewed, use Excel to look at subscribers who expired in say, the past three months (x = 3 ), and insert data columns against each churned subscriber for (a) original expiry date; (b) values = of subscriber + 30 (days); and (c) whether the subscriber renewed by the date mentioned (0 for no and 1 for yes).

If possible, also insert other information points such as: number of active days during month 1 (mandatory), active days in month 2, month 3, and so on, with each is represented by a unique column (mandatory values).

Also calculate the average number of stories read per active day for each of your top formats (such as long-form, opinions, videos, etc.), calculate the total stories read and divide by only the number of days when the user visited your platform. (also a mandatory value). You can also record the number of unique newsletters subscribed, newsletter open rates for the reader, click percentage on push notifications sent on the mobile app, and any other data points that can be used to differentiate content consumption quality, such as scroll depth.

The fourth stage is to conduct a variable analysis: Group all churned users by the number of active days during their last month of their membership, calculate renewal rate for each active day value, and plot this on a graph such as this example (based on test data and designed for demonstration purposes).

Notice that, based on the slope of the line representing the cohort renewal rate (in blue), you can easily identify the threshold of active days you could target to boost the chances of subscribers renewing.

“For example, as per this plot, increasing active days from six to 12 per month almost doubles the chances of renewal,” he says. “Similarly, increasing active days from 14 to 27+ increases renewal rate by five times.

“Similarly, doing one-dimensional analysis with other variables captured in the second step – such as ‘volume of content consumed’ by format, ‘active days’ in the first month of membership, or profiling data of subscribers – can provide interesting insights for you to act upon.”