I recently read the blog regarding data-science Wolfram Blog and then checked the quality of the new
Classify. I have a bunch of slides that I show to my students explaining classification. There I use the Titanic data from Wolfram. Here a screenshot from my slides 2016:
I´m really wondering about the new
Classify, because I now tried the same notebook with the new Mathematica version... surprise, surprise.
The data did not change, I compared with my local copy. So I doubt whether the automated data scientist mentioned in the blog has actually arrived ;-)
Classify (new) has chosen a different method which delivers a worse accuracy. So there should be other parameters on which
Classify chooses the method. Does anyone know on what parameters this decision is made?