How Shazam predicts pop hits

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.

record_player_from_1920s_Marcin_Wichary_FlickrIn 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.

Read more…


Toward a damned good information architecture

An IA model informed by an "information ecology" composed of users, content, and context.

Download a free copy of “The New Design Fundamentals” ebook, a curated collection of chapters from our Design library. Note: this post is an excerpt from “Information Architecture,” 4th Edition, by Louis Rosenfeld, Peter Morville, and Jorge Arango, which is included in the curated collection.

Users. Content. Context. You’ll hear these three words again and again throughout this book. They form the basis of our model for practicing effective information architecture design. Underlying this model is a recognition that you can’t design useful information architectures in a vacuum. An architect can’t huddle in a dark room with a bunch of content, organize it, and emerge with a grand solution. It simply won’t hold up against the light of day.

Websites, intranets, apps, and other information environments are not lifeless, static constructs. Rather, there is a dynamic, organic nature to both the information systems and the broader contexts in which they exist. This is not the old world of yellowing cards in a library card catalog. We’re talking complex, adaptive systems with emergent qualities. We’re talking rich streams of information flowing within and beyond the borders of departments, business units, institutions, and countries. We’re talking messiness and mistakes, trial and error, survival of the fittest.

We use the concept of an “information ecology” composed of users, content, and context to address the complex dependencies that exist. And we draw upon our trusty Venn diagram (see Figure 2–6) to help people visualize and understand these relationships. The three circles illustrate the interdependent nature of users, content, and context within a complex, adaptive information ecology. Read more…


Designing for ecosystems: Making meaningful IoT products and services

Mike Kuniavsky on PARC’s work on IoT and the mindset shift the IoT will require.


Attend Experience Design for the Internet of Things, our online conference where six of the smartest people working in design and the Internet of Things will share actionable advice and the essential knowledge you need to create extraordinary IoT experiences and advance your craft. Mike Kuniavsky will present “User experience and predictive device behavior in the internet of things.”

The emergence of the Internet of Things has prompted the production of thousands of new connected devices. More challenging and interesting in many ways, though, is how to embed intelligence into existing products and services. Corporations are trying to wrap their collective minds around the possibilities the IoT presents, but many don’t have the internal expertise to make sense of the space. Companies like Palo Alto Research Center Incorporated (PARC) are helping these organizations with the transition to the IoT. I recently chatted with Mike Kuniavsky of PARC. Kuniavsky is a user experience designer, researcher, and author. He is a member of the Innovation Services Group at PARC, a strategy consulting team within the research organization, formerly known as Xerox PARC.

Bringing the IoT to Fortune 50 companies

PARC has been around since 1970 and has contributed to the evolution of computing, including laser printing, graphic user interface, and the Ethernet. It should be no surprise that they are working on the next generation of computing with the IoT. Kuniavsky explains a bit more about what he and the team are working on:

The Innovation Services Group is essentially PARC’s consulting arm. Of course Xerox is still PARC’s biggest client because it’s our parent company, but it is no longer our group’s biggest client, for sure. We mostly work with Fortune 50 companies. A lot of what we do is essentially reduce the risk of adopting novel technologies through the use of user experience design and ethnography, and an innovation strategy. These days, a lot of that is in the form of looking at things that are broadly in the Internet of Things. Part of that is because that’s where my expertise is; I’ve been playing with connected hardware for 25 years. Part of it is because that’s where there’s a lot of interest. It’s gotten me to really think about the entire ecosystem that the Internet of Things is. It’s not just hooking up a sensor to the Internet and sticking it somewhere in your house. It’s a much larger ecosystem, from my perspective. That’s what we’ve been exploring a lot because that’s what’s interesting to our customers, is understanding not just how this piece of cheap commodity hardware, which can be replicated very easily by any one of their competitors, is going to create an advantage for them, but how this one specific piece of hardware is going to create an ecosystem that is going to be very competitive and is going to create significant value. Read more…


How to conduct a Design Sprint

Design Sprints bring clarity to your roadmap to kickstart and obtain initial validation for product design work.

Download a free copy of “The New Design Fundamentals” ebook, a curated collection of chapters from our Design library. Note: this post is an excerpt from “Design Sprint,” by Richard Banfield, C. Todd Lombardo, and Trace Wax, which is included in the curated collection.

A Design Sprint is a flexible product design framework that serves to maximize the chances of making something people want. It is an intense effort conducted by a small team, where the results will set the direction for a product or service.

The Design Sprint consists of five discrete phases:

  1. Understand (review background and user insights)
  2. Diverge (brainstorm what’s possible)
  3. Converge (rank solutions, pick one)
  4. Prototype (create a minimum viable concept)
  5. Test (validate with users)

A Design Sprint reduces the risk of downstream mistakes and generates vision-led goals the team can use to measure their success. For the purpose of this book, we’ll focus on digital products since our direct experience lies in that arena, though the Design Sprint has roots in gaming and architecture, and many industries have employed them successfully. Read more…


Apple Watch and the skin as interface

The success of Apple’s watch, and of wearables in general, may depend on brain plasticity.

Recently, to much fanfare, Apple launched a watch. Reviews were mixed. And the watch may thrive — after all, once upon a time, nobody knew they needed a tablet or an iPod. But at the same time, today’s tech consumer is markedly different from those at the dawn of the Web, and the watch faces a different market all together.


Apple Watches. Source: Apple.

One of the more positive reviews came from tech columnist Farhad Manjoo. In it, he argued that we’ll eventually give in to wearables for a variety of reasons.

“It was only on Day 4 that I began appreciating the ways in which the elegant $650 computer on my wrist was more than just another screen,” he wrote. “By notifying me of digital events as soon as they happened, and letting me act on them instantly, without having to fumble for my phone, the Watch became something like a natural extension of my body — a direct link, in a way that I’ve never felt before, from the digital world to my brain.”

On-body messaging and brain plasticity

Manjoo uses the term “on-body messaging” to describe the variety of specific vibrations the watch emits, and how quickly he came to accept them as second nature. The success of Apple’s watch, and of wearables in general, may be due to this brain plasticity. Read more…


Information architecture’s role in UX design

Jorge Arango discusses the state of IA and the importance of designers' understanding of context and perspective.


Jorge Arango is an information architect who has been practicing in the user experience field for more than 20 years. Before moving to San Francisco about a year ago, his work was conducted in Panama. Last year, he moved to the San Francisco Bay Area and now works as a partner at Futuredraft, a digital product design consultancy. Arango brings a unique perspective, given his background in architecture prior to becoming an information architect. He is currently finishing up the 4th Edition of Information Architecture — lovingly referred to as “The Polar Bear book” — with Louis Rosenfeld and Peter Morville.

IA’s broadening appeal

Information architecture (IA) has always been an important part of user experience design, though not always acknowledged as such. With the emergence of social, IoT, and mobile, we have watched IA taking on a more dominant role in product development. Arango talked a bit about the evolution:

I’m surprised by how many people actually know about it because I think, frankly, a lot of what we do is fairly esoteric. I’m not just talking about information architects. I’m talking about those of us in technology in general, and in the design professions. On having moved to California, I have this open question in my mind: how much do people know about this stuff here? Is it something that is talked about? I’ve been pleasantly surprised by interactions with clients and prospects … There seems to be a realization. In many cases, they probably don’t know to call it ‘information architecture’ per se, but there seems to be a realization that stuff needs to be easy to find and easy to understand.

Read more…