Important Community update: The process for changing your account details was updated on June 25th. Learn how this impacts your Community experience and the actions we suggest you take to secure your account here.
Weekly Challenges
Solve the challenge, share your solution and summit the ranks of our Community!Also available in | Français | Português | Español | 日本語
IDEAS WANTED
Want to get involved? We're always looking for ideas and content for Weekly Challenges.
SUBMIT YOUR IDEA
This was quite challenging, but also very fun! Got to learn a few new tools, and really enjoyed making one seamless workflow that's totally automated and needs no extra output files.
My solution below:
Prepping for the Expert exam so I'm doing this challenge once more. It is a weird challenge, and ultimately I ended up creating two random forests instead of a linear regression or count regression (these tools disallowed me to select a target field thanks to some magnificent bugs)
Spoiler
the drop down is broken across multiple tools and tool versions -> hooray!
I used 2 models as to ensemble them (avg)...forest models are awesome, however, these models should never be used as the population data is wrong and small, the granularity is awkward, meaning of the field names are unclear, I have some target leakage risk because of PCA,
the drop down is broken across multiple tools and tool versions -> hooray!I used 2 models as to ensemble them (avg)...forest models are awesome, however, these models should never be used as the population data is wrong and small, the granularity is awkward, meaning of the field names are unclear, I have some target leakage risk because of PCA,
