This is a guest post from Matt Fielder and Jordan Rosenblum at iHeartRadio. In their own words, "iHeartRadio is a streaming audio service that reaches tens of millions of users every month and registers many tens of thousands more every day." Personalization is an important part of the user experience, and we aspire to give useful recommendations as early in the user lifecycle as possible. Music suggestions that are surfaced directly after registration let our users know that we can quickly adapt to their tastes and reduce the likelihood of churn. But how do we personalize content to a user that doesn't yet have any listening history?

The new AI capabilities will allow iHeartRadio to revolutionize its digital music service by creating a listening experience that mimics the polished production of live radio. The new integration brings the best of live broadcast radio to digital streaming music by delivering flawless song transitions, including precise crossfades, volume leveling and truly gapless playback to iHeartRadio's listeners. "Radio DJs and programmers have mastered the art of segueing music to create beautiful transitions from song to song, maintaining the desired energy and mood of the listening experience that more than a quarter of a billion live radio listeners have grown accustomed to hearing," said Chris Williams, Chief Product Officer for iHeartRadio. "Creating transitions that are unique to each individual song combination is not an easy task, and with the billions of potential song combinations available on our platform and new ones coming every day, it was impossible to scale this by hand. Working together with Super Hi-Fi we have made the impossible, possible, and we are excited to share this new listening experience with our listeners."

Jefferson Graham shows the many options for finding audio podcasts to listen to, from apps to connected speakers, TV and the car, on #TalkingTech. LOS ANGELES -- There are hundreds of thousands of podcasts to listen to, and finding them has gotten easier than ever, thanks to apps, the connected speaker and smart TVs and streaming boxes. Remember when we had to do to acquire podcasts by connecting the phone to the computer and syncing our subscriptions? Those days are long gone. Let's take a look at just how much easier it's become.

General Motors and IBM have partnered to bring personalized content to drivers. GM's new OnStar system, which is called OnStar Go, will incorporate IBM's Watson artificial intelligence technology in an attempt to optimize the driver's time in the vehicle. But there's a catch – targeted offers and services. Thanks to IBM, OnStar Go will learn from drivers' behaviors and provide customized offers from GM's partners, which of right now include Exxon Mobil, iHeartRadio, Glympse, Parkopedia, and Mastercard. If your GM vehicle needs fuel, for instance, OnStar Go would point you towards an Exxon Mobil gas station.

In June 2016 Ravi Mody and Tim Schmeier gave a presentation at the NYC Machine Learning meetup to discuss their work on the data science team at iHeartRadio. This is the second in a three part article complementing the presentation. We recommend you read part 1 before continuing. As discussed in part 1, some of the most exciting developments in online music have been around deep personalization using machine learning. We went into detail on how we at iHeartRadio are using a machine learning method called matrix factorization (MF) to map our user behavior into powerful representations called vector space models.