In June 2019, when Piano launched the machine learning framework LT[x], we said we were putting an end to the metered paywall. Now, find out what else LT[x] (for Likelihood To [act]) can do in a new article by NiemanLab — and what we’ve learned since it was released.
“[T]his is about getting people involved beyond a single subscription and making the most of their lifetime value. How likely is it that a regular subscriber will buy an event ticket? Or sign up for another newsletter” reporter Christine Schmidt wrote, after interviews with Piano CEO Trevor Kaufman and SVP Strategy Michael Silberman.
LTs (Likelihood To Subscribe) — the first propensity model released under LT[x] — has now been rolled out to five customers, across eight sites and counting, giving us a clearer understanding of how users interact with the content on offer, and the differences that arise from site to site in predicting likelihood to subscribe.
A dynamic machine learning system is also essential to successfully predict propensity. “People’s focus on a site tends to be very intense at given periods of time … 90 days from now, your loyal audience will largely be a different group of individuals with maybe 30 to 40 percent overlap,” Kaufman said. “We wanted to make our system more adaptable to accommodate that. Having a machine learning framework to say who’s likely to churn, register and subscribe has been a critical step in us making those experiences more tailored.”
Read the full article here to find out more.