News for hackers. Stuff that matters.

A comment on Predicting Stock Performance with Natural Language Deep Learning. Parent comment

Re:Predicting Stock Performance with Natural Language Deep L... by nunya213 on Thursday May 31, 2018 @01:35PM (#17198320)
1. Are you really assuming that researchers at MSFT screwed up the training and validation sets?? 4. In what way is GBT more interpretable than an ANN??
[ Parent | on HN ]
Re:Predicting Stock Performance with Natural Language Deep L... by a008t on Friday June 01, 2018 @05:31AM (#17203838)
I don't think that was MS researchers - I think they just publicised this bit of research.

With GBT, you can check why a particular prediction was made - roughly - by navigating down each tree for a particular sample and summing up the influence of each feature on the final score. Then you can see if something weird is having a large effect on your score. Can you do something similar with ANNs?

[ Parent | on HN ]
Re:Predicting Stock Performance with Natural Language Deep L... by RyEgswuCsn on Thursday May 31, 2018 @05:13PM (#17200339)
Yes they did. I noted them in another comment.
[ Parent | on HN ]