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

Challenge #44: Inspire Europe '16 Grand Prix (L3)

Computernerd
8 - Asteroid

My Workflow

daiphuongngo
9 - Comet
Spoiler
Screenshot 2023-10-09 164958.png

daiphuongngo
9 - Comet

 

Spoiler
Screenshot 2023-10-09 164958.png

 

 

lwolfie
10 - Fireball

Great practice with the predictive tools.

Tgigs
8 - Asteroid

My solution attached. Couldnt get an accurate time because I got side tracked. Maybe wouldve been around 15 min.

 

Lowest p value was the casualty sex = male. So between male and female appears that male increases the likely hood of a fatality.

 

I feel the model could be more optimized, but was just trying to finish it as quickly as possible. For example, the model took my casualty age variable and one hot encoded it into a bunch of different features. Most or all of which had very high p values. So the age variable should likely be discretized for the model but for the sake of time I did not go through this step.

 

Spoiler.PNG

olga_strubbe
11 - Bolide

A nice challenge, thank you, @GeneR! I did not have the Regression Model as part of my Alteryx tool palette, but I was able to follow the logic for Q 4 & 5 from the model provided.   My solution attached.  

afnfyz
8 - Asteroid
Spoiler
Screenshot 2023-10-28 232408.png
Rob-Silk
8 - Asteroid

My solution and answers below:

Spoiler
challenge_44_RS_screencap.PNGAnswers:
1)  1.817008
2)  Evening, 4663
3)  Pedestrian, 2562
4)  Pedestrian (P = 0.00011, Est. = 1.86759)
5)  Male (P = 0.00968, Est. = 0.91196)

Hi all, find my solution attached

 

Spoiler
Challenge 44 solution.png

 

BS_THE_ANALYST
14 - Magnetar

Fun challenge. I ran a multi-classification problem into the logistic regression tool. Took me a couple of minutes to realise I needed to produce a dummy variable. Not sure how I feel about create a correlated variable and building a model.