Yahoo C.O.R.E. Aims To Personalize The Reader Experience In Pandora Fashion

Yahoo has a new page you can go to and see how many people are on the Yahoo homepage at any given time, as well as the most viewed stories by gender, age group, interest and city (for select cities). ...
Yahoo C.O.R.E. Aims To Personalize The Reader Experience In Pandora Fashion
Written by Chris Crum
  • Yahoo has a new page you can go to and see how many people are on the Yahoo homepage at any given time, as well as the most viewed stories by gender, age group, interest and city (for select cities).

    “More than 13 million personalized story combinations are delivered every single day on the Yahoo.com Today module, and it happens within milliseconds of someone logging on,” a Yahoo spokesperson tells WebProNews.

    She also shares the following stats:

    – More women (53%) than men (47%) read the article about Gisele Bundchen criticizing her husband Tom Brady’s teammates for the Patriots’ Super Bowl loss. In total, 67.7 million people read the article.

    – More men (56%) than women (44%) watched the recap of “The Bachelor” episode on Monday, 2/6 when a contestant was confronted about her secret boyfriend. And you thought only girls watched The Bachelor.

    – ‘Mad cow disease diagnosed in Bay Area’ tops the list of most viewed articles in the Bay Area yesterday.

    – The most viewed article in New York City today was ‘Former ‘Home Alone’ star’s startling new look.’

    The point of all of this appears to be that Yahoo’s breadth of content is serving all kinds of people with different interests, which is why the company is headed for more of a filter bubble approach – taking what you like and feeding you more of it.

    Yahoo is doing this with what it calls C.O.R.E. That stands for Content Optimization and Relevance Engine, which Yahoo Labs developed to surface stories based on interest and reader behavior.

    “Every hour C.O.R.E. processes 1.2 terrabytes of data in order to learn how a user’s behaviors and interests influence the likelihood of clicking on a specific article,” the Yahoo spokesperson says. “And, every day, C.O.R.E. personalizes 2.2 billion pieces of content for Yahoo! users.”

    “Since optimizing with C.O.R.E., Yahoo!’s Homepage click-through rate has increased 300%,” she adds. “Yahoo!’s personalization approach is a clever mix of scientific algorithms and human judgment, as editors have control to override C.O.R.E. at any time, to ensure certain stories are seen. Initially developed within Yahoo! Labs, C.O.R.E. has become a vital tool used throughout the day by editors across the company to bring our users personalized news, first.”

    In an interview with AdAge, Mike Kerns, Yahoo’s VP-social and personalizatio, likened Yahoo’s system to offerings from Pandora, Zite or Amazon. It will give Yahoo feedback, he said, so they can “start showing them very obviously that they’re seeing content based on what we know we think about you or what we think we know about you.”

    “So my wife clicks on ‘I want more of Gisele,’ and the next time we see her we’ll weight that explicit declaration along with everything else we’re personalizing based on behavior, and other people like her,” he is quoted as saying.

    Steven Lyons, Sr. Product Manager, on C.O.R.E. talks about the system on Yahoo’s Yodel Anecdotal blog:

    Today, C.O.R.E. powers content on many Yahoo! properties, including Yahoo! News and the Today Module. There, editors write and gather the most important and engaging stories of the day, and C.O.R.E. determines how stories should be ordered, dependent on each user. Similarly, C.O.R.E. figures out which story categories (i.e. technology, health, finance, or entertainment) should be displayed prominently on the page to help deepen engagement for each viewer.

    What’s unique here is not just the innovative C.O.R.E. algorithms that crunch this amount of data all day, every day – but that it’s also the perfect marriage of deep science and a world-class editorial team.

    Editors use C.O.R.E. and their editorial judgment to ensure that important stories are front and center. For example, Yahoo! editors made sure that the news of Osama Bin Laden’s death was on everyone’s page the moment the news broke. An algorithm couldn’t have done that.

    No mention is made of Yahoo Voices, which essentially took the place of Yahoo’s Associated Content content farm, but I don’t see why this wouldn’t be implemented there as well.

    Get the WebProNews newsletter delivered to your inbox

    Get the free daily newsletter read by decision makers

    Subscribe
    Advertise with Us

    Ready to get started?

    Get our media kit