Why videos recommended by YouTube sucks, and how it is about to improve

Have you ever wondered how YouTube installs itself on the algorithm that fuels their functionality to offer videos? Don't know ? Me neither, but thanks to WebProNews, now, we know that it is based on something from Amazon.com. Specifically, it is based on the "old Amazon recommendation engine." We know because of a blog entry by Greg Linden - the man who created the recommendation engine.

Now, given the current vogue, that Google has appealed to the Microsoft Bing search engine replication works, it might be easy to take this bit of knowledge and use it to beat Google. In fact, many have been fair. But that wasn't why Linden wrote the piece. It was simply pointing out how interesting it is a developed algorithm type there is more than 12 years is always the best choice for suggested YouTube videos today. In fact, many people assume that Linden was trying to criticize Google but has updated the position denying it:

For your best one stop resource for all your video marketing needs, go HERE TO THE POWER OF VIDEO MARKETING

"Update: to be clear, this was not as an attack on Google in any way." Googlers builds on previous work, as they should. What is notable here is that despite a decade of research on recommendation systems, they still work in Netflix. YouTube found a variant of the former point algorithm point collaborative filtering to fight over all others to recommend videos on YouTube. This is a very interesting result and one that validates the strengths of this old algorithm. »

All this would be totally and completely intriguing and fascinating, if it wasn't for a problem evident: videos suggested by YouTube kind of sucks. I've said before, and I am sure that I will say again. I almost never find useful videos among the group that youtube specially recommends. Has it become better? Yes... for some. But is it useful ? No, not for me... not at all.

But I'm fine with that. For some reason, I'm fine with the idea that we have not yet created the perfect mathematical formula to predict the enjoyment of the audience. I'm not sure that we can, in fact, as engineers in the world would disagree, sometimes I don't even know what kind of video I want up to the point that I usually discover one I like quite by chance. If I do not know... How can YouTube know?

There is hope, however, that the feature of recommended videos will improve dramatically - remember the acquisition of little YouTube last week? They picked up Fflick, a film recommendation engine. Is it possible that the purchase of Fflick will influence the redesign of the proposed video? Yes, I think it will. If YouTube is seriously anticipating that people will continue to spend tons of time to watch videos every day, they will need a better system of recommendation than what they now have in place.

Regardless, it's fascinating to me that an algorithm over ten years is always the current best solution to recommend videos - which speaks to the original algorithm or the difficulty in creating a good recommended video feature, I don't know that. But to compare this to the Bing controversy is apples to oranges. One appears to be blatant, thievery while the other is a job suited.

THE POWER OF VIDEO MARKETING !!