Tell me some of the things that it is  looking at ,so obvious things like if someone presses like or stay on a video for a  long time ,that give you a clue more like that . But is it subject matter ? what are the  array of things you have notice , that you can actually track that provide useful clues .
I’m going to simplify this a lot ,but the machine learning the recommendation ,algorithm   ,is really just a math . 
So for example , if you like videos ,1.2.3.and  4 , and I like videos 1,2,3,and 5. Maybe he like videos 1,2,3,and 6, now what’s going to  happen is  ? Because we like 123 at same time ,he is going to  be shown 456 ,  so are we .
And you can think about this repeat at  scale  in  real time ,across more than a billion people ,that’s   basically what it is  ,it’s  math , and of course you know ,AI and machine learning has allowed this to be done , at very very big scale , what we have seen  the result of this ,is that they learned the interest signals that people exhibit very quickly and shows you  content really relevant for you , in a very quick way .