How Pandora protects privacy and creates a better experience with first-party data

 In the heyday of broadcast radio, listener requests and record sales helped stations determine what to play and when. These days, those signals still matter, but data science enables Pandora to engage each of our 70 million listeners with song selections they didn’t even know they wanted to hear next.

The same thinking also fuels better advertising experiences at Pandora. We’re always looking for ways to fine-tune how we use our data to improve users’ experience with our products, show them more relevant ads, and meet their privacy expectations. And we’ve continued to double down on our first-party data innovations as users’ privacy expectations have increased.

But with changes driven by global regulators, device ig database manufacturers, and technology vendors, fewer third-party data signals are coming through these channels. This has forced us to prepare for the future more quickly than many web publishers who are using Chrome’s removal of third-party cookies as a catalyst for change.

 As a result, we are building new automated and intelligent solutions to amplify the impact of our first-party data now, and we are leading the way for the broader SXM Media ecosystem of which Pandora is a part.

Which classifies songs on 450 different musical a new trend in the consumption of video content: long stories or video essays attributes, informs Pandora’s core product: our incredible music recommendation engine. Our data scientists combine these attributes with user approval picks to develop the algorithm that queues up the next big song. My team uses these same data points to provide listeners with the most relevant ads, connecting them with products and services that would be most useful to their lives.

 

We can also infer things about our users and create new audience segments for our advertising clients. For example, consider what it can mean when a whatsapp filter user unexpectedly starts playing the Wiggles repeatedly through a connected speaker. Or the immediate value of knowing that a user prefers tracks with Spanish-speaking singers.

Typically, when we use listener data like this to develop behavioral audience segments, we see a dramatic increase in ad performance. For example, in a recent campaign for a quick service restaurant looking to increase repeat visits, we were able to decrease the cost per incremental visit to the restaurant locations by 190% by focusing promotions on just a handful of music genres.