Bloomberg: Personalizing the News for 20 Million People

Kevin Krim, Bloomberg, at Structure Big Data 2011Mining through terabytes and zettabytes of data isnt just for hardware companies and database-service providers media companies like Bloomberg are also trying to make use of the oceans of information they have about their users to come up with better ways of recommending news to them, Bloomberg Digital head Kevin Krim told the Structure Big Data conference in New York City today.

In an interview with Stacey Higginbotham, the Bloomberg executive described how he built a predictive-analytics team within the media conglomerate that could use the behavior patterns and usage patterns of the 20 million users who visit Bloomberg.com or BusinessWeek.com (which Bloomberg acquired last year) to make better recommendations about what topics or articles they might be interested in.

The approach that most traditional news services take, Krim said in which editors select and present the news that they think matters most to a generic reader doesnt really scale very well. But by using analytical tools on the data about those web visitors and their reading patterns and usage, Krim said that Bloomberg can present 20 million different views of that information. The company is also trying to take into account the differences in how users want to receive their news during the day, including whether they want content as text they can read on their laptop or mobile, or video they can watch, and so on.

The company now collects over 100 data points for every page a reader loads, based on what they interact with, what time of day it is, etc. more than a terabyte of data every day in aggregate, Krim said and the team has 15 different algorit! hms runn ing in parallel to make recommendations for what that reader might want to see next.

We started studying the behavior of decision makers who come to our site, Krim said, and we noticed that there are a number of different usage curves of news TV is kind of a U-shape during the day, web usage is like an arc, mobile is like an oscillating curve, magazines ramp up during the day, and newspapers obviously ramp down during the day. What Bloomberg Digital is trying to do, he said, is to understand how people move from one to the other, and then present information to them in the way that they want.

Related content from GigaOM Pro (subscription reqd):

Who uses Clickatell messaging APIs? We all do! No BS APIs so easy to integrate into your existing system, it&rsquoq;s almost criminal! Test our SMS gateway, no download required


Comments

Post a Comment

Popular posts from this blog

China Watch: Magical New Maglev, Fire the Ambassador?

Image
A list of what the Wall Street Journal’s reporters in China are reading and watching online, periodically updated throughout the day. (NOTE: WSJ has not verified items in the ‘News’ section and does not vouch for their accuracy.) Last updated: 7:22 pm Beijing time. NEWS: Chinese scientists at Southwest Jiaotong University have developed a model maglev train that runs in a vacuum tube and can travel as fast as an airplane, the Global Times reports . Whether it will ever be put to use is another question, with one expert quoted in the story calling the train “complete scientific fantasy.” The first of two planes sent to retrieve up 480 Chinese nationals stranded in Egypt has landed in Beijing, Xinhua reports . Meanwhile, Hainan Airlines today dispatched another plane to pick up some of the 300 or so who remain in Egypt. It’s not clear from the reports if all of them will fit on the third plane. CNET interviews theater/tech geek Mike Daisey, creator of “The Agony and the
Keep reading

Live Blog: GMIC G-Startup Competition 2011

Image
Technode team today is covering Global Mobile Internet Conference, both in Auditorium 1 with keynotes speakers including Charles Chao (CEO of SINA), John Liu (Google China) and in Auditorium 2 with G-Startup Competition. We will be live-blogging (and live-tweeting) G-Startup Competition here. And reporting in more details on keynotes and various interviews afterwards. Stay tuned and follow us on @technodechina #TheGMIC #gstartup ! Related posts: G-Startup Competition Prizes Announced, So Apply Now! Mobile Blog Blogging anywhere and anytime Global Mobile Game Awards at GMIC2011 Submit Your Mobile Game!
Keep reading

Chinese Pinterest Huaban.com Grabs Money and Attention

Image
Out of all the Chinese Pinterests we mentioned earlier , Huaban (, or petals) is decidedly the one that stands out from the crowd to receive US$ more than one million in Series A round of funding from KPCB, less than ten days after the website went online. The Hangzhou-based service was crafted by the startup behind Yupoo , one of the earliest and best Flickr-clone in China founded about 7 years ago. With exact the same idea, features and even web design and layout, Huaban let users collect (just like Pin with Pinterest) pictures by uploading local files or grabbing one from existing webpage. You can recollect (like Repin) whatever attractive to you and save them onto your Huaban (like board) and Like pictures collected by other users. Moreover, you can create boards under different categories to organize all the pictures you collected. Pinterest per se has seen huge growth with rapid rising traffic in the States, the site has 3.2 million UV monthly with growth rate over 100%, topped
Keep reading