Paywall that learns when to cut you off

For the last four years, The Wall Street Journal has been building a paywall that adapts to reader behavior and decides how many free (sample) articles they should get access to. This adaptive paywall is designed to drive subscribers and communicate the value of joining the Dow Jones family.

The Wall Street Journal's paywall houses a machine-learning algorithm that measures reader activity across 60 variables including visit frequency, recency, depth, favored devices and preferred content types. This forms a propensity score, a unique subscription probability, that then helps inform how many sample stories users can access. In short, reader activity shapes how much Wall Street Journal content they can sample.

Over the last few years, the WSJ has operated a deliberately leaky paywall that has served as a sandbox of data collection and subscription sale experiments. The principle is to "sample content to people that we know need it". By doing so their likelihood of subscribing will rise. On the flipside, by regularly offering free content to assumedly affluent individuals who often visit the site, the value of the content falls.

While most paywalls on the market offer a one-size-fits all approach (a hard paywall won't budge, a metered effort will limit everyone to the same volume of articles), by making a more complex system, the WSJ has learned just how long users have to be engaged with the brand before they make a leap for the subscription. In short, The Wall Street Journal carefully allows users to take a test drive of the site.

The issue with the other models was that they assume that every buyer has the same "tipping point", the same threshold. Users who delve beyond the business content in the arts, culture or columns are generally more likely to subscribe too. "Those showing the strongest intent to subscribe are those that actually understand the fullness of our product." By using these techniques to create dialogue with readers, WSJ claims to have attracted some 350,000 student sign-ups, largely with greatly reduced flash sales.

Original article published by The Drum