Machine Learning for Publishers: Using Behavioral Science to Build Better Paywalls
This talk will cover lessons from The Wall Street Journal's two-year initiative to reimagine its paywall with the application of machine learning techniques. It will address ways publishers today can use predictive analytics to optimize paywalls for both macro trends (i.e. advertising capacity) & individual users' behavior (i.e. a person's unique pattern of readership). Utilizing a credit score of sorts, complex readership patterns can now be distilled into actionable indicators of a reader's likelihood to subscribe (or alternately, to churn or select a certain subscription type).
At the Journal, these scores are used to test different paths for readers. This means altering messaging & access in such a way to incentivize engagement among low propensity readers, keep the paywall tight for those ready so subscribe, & nudge readers along that path to subscription.
The session will include several live coding examples, & also offer some proposals for how similar modeling techniques can be applied in other industries like eCommerce & finance.
John Wiley is associate director of data science & analytics at The Wall Street Journal, where he manages a team focused on applying predictive analytics in the Journal's membership business.
In collaboration with the Journal's Product, Design, & Engineering (PDE) team, he helped develop a suite of machine learning applications enabling the dynamic targeting of paywall experiences based on a reader's probability of subscribing.
In 2018, the project was recognized with top distinctions by both the International News Media Association (INMA) & the Direct Marketers Association (DMA) ECHO Awards. John holds a bachelor's degree in information systems & business analytics from Boston College's Carroll School of Management.