Polls said Trump was popular, but Herman Cain was also popular. Difference was changed dynamics. Smart "pundits" caught that, models cannot.
A US electoral expert, for ex., would raise eyebrows at, say, poll with too white likely voter scenario. Similar.
-
-
Predictive analytics is better with high frequency events with loads of data. Presidential elections are rare.
-
Which means data won't tell you when your model needed to shift. Expertise will alert you something is amiss.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.