search

InseadDataAnalytics / INSEADAnalytics

Other
122 stars 1.31k forks source link

New dataset ideas #159

Open aniketvshende opened 5 years ago

aniketvshende commented 5 years ago

Are there any ways to know which Data Science competitions are for intermediate users?

tanmayi-91 commented 5 years ago

I think we should consult Christos

tanmayi-91 commented 5 years ago

Hello, which dataset?

tanmayi-91 commented 5 years ago

PEtfinder.com is great

Duezz commented 5 years ago

How about an accident prediction?

harindun commented 5 years ago

Check this out! https://www.drivendata.org/

nkrarick commented 5 years ago

Let's use the Zillow dataset

aniketvshende commented 5 years ago

Thanks all

aniketvshende commented 5 years ago

Solution to our dataset https://www.kaggle.com/reginashay/petfinder-xgb

aniketvshende commented 5 years ago

https://www.kaggle.com/reginashay/petfinder-xgb

nkrarick commented 5 years ago

Hey folks,

I updated the rmd file and it's in your inboxes. Milli is sending histograms/graphs via email now with additional data visualization (we can include these) and we also noted a few other things.

  1. We probably want to remove all data where quantity > 1 (it poses a weird gender issue)
  2. We might want to run the classifications again with two separate data sets - 1 for dogs and 2 for cats since different factors might determine if they are adopted or not.