"user behavior" entries
The O'Reilly Radar Podcast: Cait O'Riordan on Shazam's predictive analytics, and Francine Bennett on using data for evil.
Subscribe to the O’Reilly Radar Podcast to track the technologies and people that will shape our world in the years to come.
In this week’s Radar Podcast, I chat with Cait O’Riordan, VP of product, music and platforms at Shazam. She talks about the current state of predictive analytics and how Shazam is able to predict the success of a song, often in the first few hours after its release. We also talk about the Internet of Things and how products like the Apple Watch affect Shazam’s product life cycles as well as the behaviors of their users.
Predicting the next pop hit
Shazam has more than 100 million monthly active users, and its users Shazam more than 20 million times per day. This, of course, generates a ton of data that Shazam uses in myriad ways, not the least of which is to predict the success of a song. O’Riordan explained how they approach their user data and how they’re able to accurately predict pop hits (and misses):
What’s interesting from a data perspective is when someone takes their phone out of their pocket, unlocks it, finds the Shazam app, and hits the big blue button, they’re not just saying, “I want to know the name of this song.” They’re saying, “I like this song sufficiently to do that.” There’s an amount of effort there that implies some level of liking. That’s really interesting, because you combine that really interesting intention on the part of the user plus the massive data set, you can cut that in lots and lots of different ways. We use it for lots of different things.
At the most basic level, we’re looking at what songs are going to be popular. We can predict, with a relative amount of accuracy, what will hit the Top 100 Billboard Chart 33 days out, roughly. We can look at that in lots of different territories as well. We can also look and see, in the first few hours of a track, whether a big track is going to go on to be successful. We can look at which particular part of the track is encouraging people to Shazam and what makes a popular hit. We know that, for example, for a big pop hit, you’ve got about 10 seconds to convince somebody to find the Shazam app and press that button. There are lots of different ways that we can look at that data, going right into the details of a particular song, zooming out worldwide, or looking in different territories just due to that big worldwide and very engaged audience.
Pilgrim Beart on AlertMe, and IoT’s challenges and promise.
I recently sat down with Pilgrim Beart, co-founder of AlertMe, which he recently sold to British Gas for $100 million. Beart is a computer engineer and founder of several startups, including his latest venture 1248.
Identifying the gap between technology and consumers: How AlertMe was founded
I asked Beart about the early thinking that led him and his co founder, Adrian Critchlow, to create AlertMe. The focus seems simple — identify user need. Beart explained:
I co-founded AlertMe with Adrian Critchlow. He was from more of a Web services background … My background was more embedded technology. Over a series of lunches in Cambridge where we both lived at the time, we just got to discussing two things, really. One was the way that technology was going. Technology push — what changes were happening that made certain things inevitable, and also consumer pull. What were the gaps that technology wasn’t really addressing?
To some extent we were discussing at quite a high level the intersection of those two, perhaps not quite in that rational way, but as we talked about things we were interested in, that’s essentially what we were doing. We were triangulating between the technology push and the consumer pull, and trying to spot things that essentially would be inevitable because of those two things. Then that led us to thinking about the connected home platform and what could the killer apps for the connected home be, and isn’t it strange how, if you compare the home to the car for example, cars have a large number of computers in them, and the computers all work together seamlessly and invisibly to keep you safe, keep you secure, save you energy, and so on.
In the home, you have a similar number of computers, but they’re not talking to each other, and as a result, it’s really far from ideal. You have no idea what’s going on in your home most of the time, and it’s not energy efficient, it’s not secure, etc. We saw a huge opportunity there, and we saw the potential for some technological advances to help address those problems.
Twitter isn't quite beyond jumping the shark, but it has taken a big step backward.
While I’ve been skeptical of Twitter’s direction ever since they decided they no longer cared about the developer ecosystem they created, I have to admit that I was impressed by the speed at which they rolled back an unfortunate change to their “blocking” feature. Yesterday afternoon, Twitter announced that when you block a user, that user would not be unsubscribed to your tweets. And sometime last night, they reversed that change.
I admit, I was surprised by the immediate outraged response to the change, which was immediately visible on my Twitter feed. I don’t block many people on Twitter — mostly spammers, and I don’t think spammers are interested in reading my tweets, anyway. So, my first reaction was that it wasn’t a big deal. But as I read the comments, I realized that it was a big deal: people complaining of online harassment, trolls driving away their followers, and more.
So yes, this was a big deal. And I’m very glad that Twitter has set things right. In the past years, Twitter has seemed to me to be jumping the shark in small steps, rather than a single big leap. If you think about it, this is how it always happens. You don’t suddenly wake up and find you’ve become the evil empire; it’s a death of a thousand cuts. Read more…