Vipul Sharma, director of data engineering for Eventbrite, spoke at GigaOM’s Structure:Data conference in New York on Thursday about the data challenges facing his company, which fields customers and data from across the globe. By June 2012 the company had crossed $1 billion in ticket sales, and Sharma said Eventbrite has hosted more than a million events so far.

Sharma,who has worked as an engineer since 2010 after leaving Digg, where he worked on data mining and machine learning, said one of the biggest data challenges Eventbrite deals with is the speed of the flow of information:

“So basically what I’m trying to tell you is that the challenge in solving realtime is two-fold. One is the data flow, or how do I transfer the data I have in realtime to my downstream applications,” he said. “And the second part is processing, or how do I process this significant amount of data in realtime. To process in realtime you really need a distributed processing system.”

Check out the rest of our Structure:Data 2013 live coverage here, and a video embed of the session follows below:

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Big data budgets on the rise
• Why the next front in big data might be psychological
• What’s driving the next phase of the e-commerce evolution

The trick to doing recommendations right, according to Eventbrite Director of Data Engineering Vipul Sharma (who will be speaking at our Structure:Data event in March), is rooted in both business and data architecture. Companies must know who their audience is, what types of data they can collect and how they can best use that data to discern what consumers really want. Or, to put it more succinctly, companies have to understand data science.

The Amazon microcosm

Amazon is a good example of the approaches a company might take. The e-commerce giant, Sharma explained, used to use a hierarchical model to recommend additional purchases to shoppers. Products were indexed in such a way that, for example, the system would always recommend batteries to someone buying a camera. However, as the product catalog grew and Amazon picked up its analytical abilities, it moved to the current model of recommending purchases based on what other people who bought the same thing also bought.

Now, Amazon is able to present more accurate suggestions because it’s using real-world purchase data instead of static indexes that make assumptions about what someone should buy. Presenting this information as “Customers Who Bought This Item Also Bought” is not only a way to sell more stuff, it also provides shoppers the peace of mind of knowing they’re pairing items that — if the wisdom of the crowd is to be believed — go well together.

Of course, Amazon also uses a process called collaborative filtering to make recommendations to members even before they start looking at individual items. These recommendations aren’t based strictly on products that are frequently bought together, but also on how shoppers with similar purchase histories and interests tend to behave. Amazon actually explains the process pretty clearly on its Recommendations FAQ page:

We determine your interests by examining the items you’ve purchased, items you’ve told us you own items you’ve rated, and items you’ve told us you like. We then compare your activity on our site with that of other customers, and using this comparison, are able to recommend other items that may interest you.

Down, I like. Otep, not so much.

But Amazon does have one trick up its sleeve that many other companies don’t: Shoppers spend a lot of time on its site and many of them might actually be willing to put in a little effort to get more-accurate recommendations. So, Amazon is able to build even better recommendations for users by asking them questions about recommended items — do they own it, do they like it, and is the purchase that spurred the recommendation worth using for future recommendations. The better the information a company has about what users actually want, the better recommendations (or ads) it can show them.

Everyone does it different

However, Sharma explained, every web company has its own unique methods for making recommendations. Facebook, for example, relies on users’ social graphs to make recommendations based on what someone’s friends also like (it also relies on users’ stated interests primarily to serve ads). It’s a platform built on the idea of connecting with friends, so it assumes users care what their friends are up to and are interested in.

Netflix takes a different approach (its Facebook Connect feature notwithstanding), focusing its recommendation efforts around items. Its algorithms are about calculating the relationships among pieces of content based on factors such as genre, actors, ratings and even the sequence in which users typically watch stuff. Personalization in this case is more interest graph than social graph — Netflix knows what you like (or at least what you’ve watched) and suggests new content that’s somehow similar to it or related to it. As I explain here, a graph is essentially a method for storing data based on their relation to each other.

Source: Netflix

(Some, however, have suggested that clustering users based on their interests first might make content recommendations more accurate, because, they argue, what others with the same interests are watching is probably more relevant than how the content itself is related.)

In June, my colleague Stacey Higginbotham wrote about the mysteries behind Apple’s Genius recommendations in iTunes. The methods actually don’t seem too out of the ordinary, but a Quora post explaining them did get pulled …

Eventbrite’s “implicit social graph”

In order to accurately recommend events for its members to attend, Eventbrite has to use a combination of all these tactics. Its model takes into account what events someone has attended in order to discern and graph their interests, Sharma explained, but also builds what he calls an “implicit social graph.” The people in this graph aren’t necessarily a user’s friends, but rather are people who frequently attend the same conferences.

“We internally treat them as your friends and believe they’re part of a social graph because you share an interest with them,” he said. For Eventbrite’s purposes of recommending new events a user might like, if someone is always attending country music festivals or big data conferences, his peers are the people attending those events.

Eventbrite actually does use Facebook Connect, Sharma noted, but clarified that “it’s useful, but it’s not really great for us.” People don’t update their interests too often, he explained, and someone’s personal interests don’t necessarily align with their professional interests. And although Sharma didn’t mention it, others in the business of building interest graphs have noted that the interests people express publicly in front of our friends and family don’t always align with the interests we express by acting in certain ways.

Another wrinkle for companies, such as Eventbrite, that are more services than platforms is that users probably aren’t willing to stick around and answer questions to help the sites build better models. Amazon and Netflix users might provide express feedback on recommendations, and Sharma noted that even Facebook can assume users are less interested in particular friends when they block certain updates or actions from them. Because users aren’t addicted, he said (or perhaps because they don’t attach the same importance to events as to the movies they watch), Eventbrite’s approach to learning what users want has to be frictionless.

I’m not a member, so Eventbrite can only assume I want local events

And while the talk today is all about social graphs and interest graphs, Sharma thinks the future of online suggestions is object graphs. No longer will it be good enough just to know a user is into music, but companies will also have to know what instrument she plays. This will be more difficult for companies that can’t simply ask users about their specific interests, but Sharma said it’s now so easy (relatively speaking) to collect lots of data both internally and from other web services, and analyze it deeply, that this level of specificity should be possible even for small data science teams.

Personalization, after all, is a popular method by which web services prove their worth. Netflix claims that 75 percent of what people watch comes from some sort of a recommendation. As for Eventbrite, Sharma said, “We are not a subscription product, but when people love the product, they stay with the product.”

Feature image courtesy of Shutterstock user Ivelin Radkov.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Infrastructure Q1: Cloud and big data woo enterprises
• A near-term outlook for big data
• 9 Companies that Pushed the Infrastructure Discussion in 2010

This is the problem that Vamos, an event discovery app that launches today, is trying to solve. Right now it’s only available through iTunes, although an Android version is apparently on the horizon too.

Of course, other apps are also trying to update the listings business. TimeRazor takes a curated approach, and Time To Enjoy blends local discovery with ‘to-do list’ functionality.

But the smart thing with Vamos is that it’s not a straight listings service – instead, it aggregates public Facebook events that you, your friends and other Vamos users have been invited to, and overlays them on a map.

On top of this social graph action, the app also pulls in Instagram photos that are being uploaded at the location of nearby events, so you can see if the party has really started. It also synchronises its own RSVP system with that of Facebook.

“Facebook is helping us to work on day one, but we’re also working on integration with Eventbrite,” co-founder Luis-Daniel Alegria told me. “We’re not competing with Facebook events – we work in symbiosis with Facebook and other event platforms out there.”

Right now Vamos eschews the category-centric presentation of traditional listings, instead opting to let users filter events by time, friends, location and event type if they want. I actually quite like this, as it encourages serendipity and avoids the problem of mis-categorization, but they’ll probably have to become more category-driven as the events becomes too numerous to handle in one morass.

The company is, so far, a bootstrapped affair. So how’s it going to make money?

“We have thought about a couple of ideas,” Alegria said. “Venues that want to attract more people will be able to know who has their app open. They know which target audience they want to reach, so they’ll be able to do a promoted or featured event – we we’ll only introduce that once we have a good userbase, though.”

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• The fourth quarter of 2012 in mobile
• Connected consumer third-quarter 2012
• Mobile 2012 and beyond

As Amiando’s founders prepare their valedictory speeches (they’re off to formulate a new venture soon), the company has published a number of selected statistics, showing how well they’ve been doing “on the international road”.

The company says it’s been used to organise “over 180,000″ events worldwide now. Overall, year-on-year sales growth for the period of January to May 2012 was “over 100 percent”. Growth in the U.S. (where Amiando doesn’t even have an office) is “about 150 percent”, and in the UK and Asia (where it does) it’s “over 135 percent”.

Presumably this is intended as a way to front up to Eventbrite, the American event service that says it’s targeting Europe as it expands globally.

The frustrating thing, of course, is that percentage increases are very difficult to interpret when you don’t know the base. And unfortunately, as Xing is now the daddy, the Amiando team was unable to help me out there.

I’m willing to accept that the overall sales growth looks good. The company’s been going for six years. It’s not the 200 percent growth Amiando was quoting in 2009, but it’s impressive enough and — presumably — must come from a fairly solid base at this stage in the game.

Beyond that, I don’t know what to make of it. Around two-thirds of Amiando’s business is still in Germany, meaning the rest still forms a relatively low proportion, even with the London office opening this year and Paris and Hong Kong offices opening last year. So the higher growth figures there (except for France it seems, which isn’t mentioned) could be less impressive than they first seem.

The free-floating figures quoted on Thursday certainly don’t tell us much when trying to compare Amiando’s success with Eventbrite’s. The last metrics we got from Eventbrite was the sale of its fifty-millionth ticket in February and the milestone of $1 billion of tickets sold last month — sadly, not comparable to any of Amiando’s stats.

But hey, even if the numbers don’t say much, they do look good as an end-of-term report for Amiando’s soon-to-depart founders, and as an early-days reflection on Xing’s stewardship of the business. Onwards and upwards!

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Google and the Ghost of Silicon Valley Past
• Will cloud computing push the BRIC market to the front?
• Facebook’s tactical retreat on privacy

No, it’s not a holiday.

Amiando, whose system powers such conferences as LeWeb, along with other live shows, announced on Tuesday that CEO Felix Haas, CFO Sebastian Bärhold, biz-dev chief Dennis von Ferenczy and CTO Armin Bauer will leave at the end of August. The move comes at the end of a transition period planned when social networking company Xing bought the German firm for €10 million a year and a half ago.

The new CEO is Norbert Stockmann, who’s jumping over from his head role at rival outfit Ticket Online. He’ll be working alongside verticals VP Julian de Grahl, with the two forming what Amiando calls a “management duo.”

But what about the founders? Flush with cash, it seems they’re off for a deserved break – then an intriguing return.

“We are planning on starting a new venture together,” von Ferenczy told me. “When we leave the company we’ll probably take a few months off, go travelling a bit and get some new ideas.”

He added that the new business would probably be internet-related, “to leverage the experience we got from the last few years together”. But that’s all he’ll venture for now.

As regards to Amiando, all is good, it seems. “The collaboration with Xing has been very good over the past one and a half years,” von Ferenczy said. “It’s running very smoothly.”

The Amiando founders’ new operation should start to reveal itself around the end of this year or the start of 2013. Given their successful exit and the success of the company they’re leaving behind, I think it’ll be wise to watch this space…

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Google and the Ghost of Silicon Valley Past
• Will cloud computing push the BRIC market to the front?
• Facebook’s tactical retreat on privacy

The most neglected fact in business is that we’re all human.
– Chip Conley, founder of Joie de Vivre Hospitality

We humans are an extraordinary bunch. When inspired, humans can accomplish amazing things – from enabling flight to creating microprocessors to putting a man on the moon. As incredible as humans can be, we are fundamentally wired to maximize our chances of survival and our social status. This makes us highly susceptible to the cultural norms and principles of those around us.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• 12 tech leaders’ resolutions for 2012
• Flash analysis: the tech startup investment environment, Q3 2011
• Millennials in the enterprise, part 1: strategies for supporting the new digital workforce

What’s social event discovery, you ask? Chances are good that you’ve attended an event in the recent past that used an event registration system called Eventbrite. Eventbrite provides an easy-to-use event registration system for organizers that handles both paid and free events. Eventbrite also provides social media integration tools to allow attendees to quickly broadcast their event plans to their friends, fans and followers as soon as they’ve registered for an event.

Because Eventbrite has been providing event-booking services with social media integration for several years, it can now add new features to help attendees who have previously registered for an event through the system find new, relevant events to attend. If you have bought a ticket or registered for an event using Eventbrite and linked the site with Facebook through Facebook Connect, Eventbrite canl now give event recommendations pulled together from data about your Facebook friends and the events they’re attending. When you click on the “Facebook Recommendations” tab, you are experiencing the power of social event discovery. If you are looking for new events that you can attend, where better to look for information than those with whom you’re connected on the social graph? Eventbrite also hopes to add more recommendation streams from other popular social networks such as LinkedIn sometime in the future.

Another tool that is gaining popularity is Plancast, a site entirely based on the act of sharing the events you are planning on attending. You can follow others to see what plans they broadcast, and others can follow you. You can add yourself to an informal attendee list for an event by clicking the “count me in” button, which all help to create an engine for social event discovery. While the travel site Tripit also has a similar plan-sharing aspect to it, it doesn’t get as granular as identifying the specific events you’re attending; it only shares planned trips based on cities where you’re traveling.

On Plancast, conversations ensue once people start connecting to event plans and posting messages about the upcoming event and related activities. For example, right now there is a great deal of chatter around Blogworld and New Media Expo happening in Las Vegas later this week. You can discover new events by seeing announcements of the plans of people you follow, and also through a list of related events on every event page. For example, from the Blogworld plan page you can link to Scott Stratten’s pre-Blogworld Tweetup.

I’m finding social event discovery to be useful to tool learn about new events that I may not hear about otherwise, particularly regional events and events in industries different from my own. And I appreciate the intelligent recommendations that come from mashing up event attendance and event plans with one’s social graph.

Disclosure: Plancast is backed by True Ventures, a venture capital firm that is an investor in the parent company of this blog, Giga Omni Media. Om Malik, founder of Giga Omni Media, is also a venture partner at True.

Related content from GigaOM Pro (sub. req.):

• Enabling the Web Work Revolution
• Report: The Real-Time Enterprise
• Social Media in the Enterprise

While “D” is getting awfully high in the alphabet for a web startup, Eventbrite CEO Kevin Hartz said he’s not prepping for an IPO anytime soon. “If you see what’s out there on the ticketing side, there’s just not a lot of innovation — it’s been a status quo industry,” he said. “We’re really just getting started.” Still, $20 million is no joke, and puts pressure on the company to show its early momentum can mean a real business.

Hartz said Eventbrite is on track to do $200 million in gross ticket sales this year; the site’s average ticket price is $60. With a per-ticket fee of $0.99 and a 2.5-3 percent cut of every transaction, that’s (my math, not his) at least $8 million in revenue.

Hartz told me he believes Eventbrite mainly serves customers who previously didn’t use a ticketing vendor. “We’ve primarily been an enabler — we’ve been enabling a whole new class of events,” he said. Asked about taking down the vile Ticketmaster and its evil fees, Hartz started to demur but then replied, “It’s very natural that at some point we’d push upstream.” He pointed out that Eventbrite isn’t directly competitive with Ticketmaster yet because it doesn’t offer reserved seating.

For now, Eventbrite is focused on innovation around things like ticket demand. For instance, after integration with Facebook Connect to encourage users to share events, Facebook is now Eventbrite’s largest referrer of traffic.

Related content from GigaOM Pro (sub req’d):

• New Use For Web Stats: Finding Hot Markets, Offline
• Location: The Epicenter of Mobile Innovation
• Social Advertising Models Go Back to the Future

Mobile ticketing generally means visually inspecting tickets sent via SMS or scanning barcode images on your phone. But a new San Francisco start-up called MogoTix, launching Thursday, wants to make mobile ticketing fully mobile on both ends, by enabling event holders and attendees to transact using mobile phones.

Event producers can go to MogoTix.com and create a custom web site for their event, from which they can sell tickets, just like Eventbrite. The tickets are then sent via picture message to users that appear like 2-D bar codes.

At the event, organizers can check in guests using a MogoTix iPhone app that scans the tickets. The system can let multiple organizers see who’s checked in, broadcast the names of guests as they arrive and send out alerts to guests a few hours before the event. For users, the benefit is less chance of losing your ticket. You just need to have a phone.

Mobile ticketing is forecasted to grow to 15 billion delivered tickets by 2014, according to Juniper Research. MogoTix hopes picture messaging and mobile ticket-scanning will give it some differentiation.

The company received $115,000 in funding two months ago by a group of angel investors led by Dave McClure and his 500 Startups fund. MogoTix is led by Scott Thorpe — founder of Fynspire, a web development company — and also gets advice from Cass Phillipps of FailCon fame and James Goodman, who built Ticketmaster Online and was one of the first employees of Tickets.com.

Related content from GigaOM Pro (sub req’d)

How to Market Your iPhone App: A Developer’s Guide

Will Metered Mobile Data Slow the App Market’s Growth?

The App Developer’s Guide to Choosing a Mobile Platform

Services such as Yahoo’s Upcoming and Meetup and Facebook’s Events, coupled with a decentralized and grassroots meetup and “unconference” culture have led to an explosion of event invitations in our various inboxes. That first generation of tools is looking a little creaky to today’s event planners, so here’s a roundup of the current generation of “eventware.”

The current generation of eventware all offer a mix of registration, ticketing, mailing list, analytics, payment and promotion features, but each is pretty distinct in its niche:

• Amiando. launched in 2006, Amiando powers some of the European tech industry’s larger, more formal conferences, including Thinking Digital and Le Web. Though private events can be listed for free, public events incur an excessive €1 + 6 percent of the ticket price for each ticket sold. However, the service includes some unique features, including comprehensive Facebook integration and the ability to run an entire conference site from within the app.
• Eventbrite. I can’t think of a week that goes by without receiving multiple invitations to Eventbrite-powered event (including GigaOM’s own conferences). It’s a great solution, with a very vocal and engaged development team constantly providing new features, though the interface can sometimes be a sprawling mess and it’s easy to forget how a previously completed task was completed. Eventbrite’s real power lies in the ability to quickly list and promote an event without too much effort.
• Expectnation. Heavily utilized by O’Reilly Media’s conference team, what’s unique about this service is the ability to manage session proposals, calls-for-participation and manage a conference’s schedule and structure, as well as the sales and ticketing processes. It’s a pretty comprehensive solution, though the absence of pricing information suggests it’s a very premium choice.
• OpenConferenceWare. Perhaps the most interesting development is the open-source OpenConferenceWare project where the creator’s motives were to offer a free and open app to empower others in creating events. It was most prominently utilized in 2009′s Open Source Bridge conference. Like Expectnation, OpenConferenceWare provides features to manage submissions and schedules, but also enables delegates to personalize custom schedules for their attendance (just like SCHED*, reviewed here). Unfortunately, as an installable app, setup requires some knowledge of Ruby and web hosts.

Amiando, Eventbrite and Expectnation are fully formed and comprehensive suites for event planners; albeit expensive. However, I’m intrigued by OpenConferenceWare’s philosophy; with the groundswell in this software category, could OpenConferenceWare evolve into the WordPress of its segment?

If OpenConferenceWare was as easy to customize and install as WordPress, we could see a sophisticated and proven free alternative to the big commercial solutions as well as a vibrant ecosphere of plugin and theme developers. Even a hosted, freemium service — like WordPress.com (please see disclosure at the bottom) — could outmaneuver larger competitors.

Which event planning and ticketing solutions do you use?

Disclosure: WordPress.com is backed by True Ventures, a venture capital firm that is an investor in the parent company of this blog, Giga Omni Media. Om Malik, founder of Giga Omni Media, is also a venture partner at True.

Related GigaOM Pro content (sub. req.): Report: The Real-Time Enterprise

Photo by Flickr user LornaJane.net, licensed under CC-BY-ND 2.0