Re:Machine learning predictions for QM eMini Crude Oil
by minimaxir on Tuesday September 26, 2017 @12:09PM
(#15339925)
A statistical model based on bad/dependent features is essentially just random guessing, which in this case the model just makes favorable guesses.
[ Parent
| on HN ]
Re:Machine learning predictions for QM eMini Crude Oil
by madchops1 on Tuesday September 26, 2017 @02:21PM
(#15341278)
I experimented with the features until I got good results in my evaluations. If I am getting favorable guesses, how does that point to bad features. Favorable guesses is what I was going for in order to assist in trading decisions.
I use a 70/30 split of training/eval