Introduction to Decision Tree Learning

Re:Introduction to Decision Tree Learning by pcprincipal on Thursday April 26, 2018 @11:56AM (#16933016)

This is great and has an awesome level of detail on information gain. I have found decision trees really useful for getting a feel for what features in a dataset matter and trying out different max depths on trees to get more insight into the data.

I wrote an article earlier this year on how I use decision trees to classify players for daily fantasy sports into different groups that people may find useful https://medium.com/@bmb21/why-is-caris-levert-projected-for-...

[ Parent | on HN ]

Re:Introduction to Decision Tree Learning by claytonjy on Thursday April 26, 2018 @03:56PM (#16935087)

I use RF's commonly for getting that same feel, but I recently learned that I've been making some big mistakes when interpreting default feature-importance outputs; this recent article really opened my eyes: http://parrt.cs.usfca.edu/doc/rf-importance/index.html

Short version: always use permutation importance, but use leave-it-out importance when it really matters

[ Parent | on HN ]

Re:Introduction to Decision Tree Learning by ishansharma on Thursday April 26, 2018 @12:02PM (#16933087)

Thank you for the kind words. My goal was to make the explanations as simple as possible.

Using them to get a feel about dataset is an interesting use case and I haven't tried that. It does sound interesting though. Something to do with my next ML problem I suppose. :)

Just skimmed through your article(class final exams tomorrow), it is informative. Thanks for sharing.

[ Parent | on HN ]