Search has been one of the most powerful tools on the internet, but its next of kin “discovery” is coming up fast. Many new sites are serving up recommendations alongside search to help visitors discover new content they didn’t even know they wanted. But implementing a discovery engine yourself can take time and money away from your core product. Isral-based Taboola will solve that rather complex problem, for video sites at least. They’ll be announcing $1.5 million in financing tomorrow from Evergreen Venture Partners .
Taboola’s made integrating their system a breeze. All it takes is a single javascript tag added to your player’s code for them to start recommending videos in your site’s player (or ads, as seen right). You can currently see their service live on 5min. Taboola says that 5min has seen a 23% increase in watched videos and 53% increase in session length.
Their engine makes recommendations based on a rather complex algorithm that combines multiple methods into a single “Match Rank” — collaborative filtering (user ratings/reviews), a viewer’s history, and analyzing the video’s meta data. Their claim is that each one alone is prone to problem, but together can cover for each other’s short comings. The system even takes into account small details, like the length of a video or how much of the video people actually watched.
It’s a pretty beefy algorithm under the hood. However, the general idea is that their system sorts through your video content, then recommends them to users based on what they and users like them have watched in the past. If you want to get into the details, you’ll have to request a demo. However, it looks like a good solution for websites not looking to reinvent the wheel, but instead focus on their core product.
I see the launch of services like Taboola as a sign that the online video space is really maturing. We’re past the days of video sites having to hack away at all their problems alone. New services are popping up to meet the individual needs of publishers looking to make the transition online more easily. There are services for serving video advertising, trans-coding, and even video hosting.
great product
Goog recommendation engine.
http://www.meet...earchVideo.aspx
Blazing fast VIDEO SEARCH ………………..:-)
Looks like a super complex version of stumbleupon for videos?
Content discovery for video seems to be the next big thing but what about silent startups like Arkayne.com that have been working on impressive algorithms for textual content discovery. Isn’t video just text in picture form?
You may have noticed it in the TechCrunch forums, or on one of your favorite sites. The Arkayne content discovery engine has just released a new API and is growing by about 200 pages a day, recording a few K hits a day since launching beta a month or two ago.
Ultimately content discovery will have to belong to an entity like Google and serve video, audio, and text. The only trick will be an API that is robust enough. Several mash ups come to mind. The content discovery algorithm at Arkayne seems like a pretty good candidate…
http://www.arkayne.com
A french startup Criteo.com vc backed is also doing something like that but not only for videos (they did with Youtube videos for example)
Hey, just small typo: Isral-based Taboola , but I guess that by the time you get to correct it Taboola will be on the death pool
I tried the 5min website. Hmm…the recommendation list isn’t terribly exciting. I like cars. So I started with a video on how to start a dead battery. At the end of the video, I was recommend a video on how to ride a motorcycle.
So what gives??
Love the concept. Would be great if it monitors your viewing habits among many sites/players to further fine-tune the videos it displays.
At VeZoom, we have created the largest database of Video index and have been working on our recommendation engine. The algorithm is even more complex and comprehensive than Taboola but for the users they will get the video they really want.
I’ve checked out a video about how to facebook and was recommended with facebook which make sense, and got another video at what they call “people like” with “how to download media” which means – it doesn’t talk about facebook, but it is in the world of online internet.. i actually watched that after the facebook video… now, i dont know how they do that, cause it seems too good to be automatic … if its automatic, respect
Is it true that Taboola learns who am i so that the recommendation list will get better over time?
would be interested in an answer.
Liz moderating