Challenge #18: Predicting Baseball Wins

[GabrielaTudor]

Spoiler

[lwolfie]

This was definitely something I don't use on a regular basis.

[jon_amanrich]

Need to work extra on predictive tools 😅

[gawa]

I suppose that correlation strength should be evaluated based on absolute value, not just descending order, although doing so will not match solution. In order to fit output, I have to compromise about it anyway...

Spoiler

[gawa]

Post with solution file

[MartinStraech]

First time doing a Predictive challenge, which is a big part of my current role.

Spoiler

[MitchellBliesner]

After taking a break, I want to get back into solving challenges. 

[caltang]

Done!

Spoiler

[danielhoge]

Spoiler

I used Pearson Correlation to find the top 10

[Tgigs]

My solution attached.

Made the selection of the top 10 variables dynamic by using pearson correlation and joining it back in with the original data to dynamically select the top 10 correlated variables.

Had to check the solution to get some clarification, was a little unclear on the directions. Tried to use the 6 teams filtered for training the model and that resulted in an error. Then found out all data is used for training and then just the 6 filtered teams for applying the trained model and making the predictions.