-
Notifications
You must be signed in to change notification settings - Fork 1
Description
The goal of the project is to analyze whether a player against a certain type of pitcher will hit, whiff, or take during play. This is meant to be used for managers to determine good team compositions and how to properly train a team to be successfully when on offense. The person handling the data determined that the pre-filtered data was already good enough so in terms of missing data, it was not problematic in that regard. However for data cleaning, the individual removed irrelevant columns and encoded the description data to be usable for the model.
Positives for project:
-Plentiful amount of reliable data which can result in a reliable model
-Your next steps seem ambitious and can improve your model significantly
-Data cleaning seems well done to easily create models using what we learned in class as well as other possible modeling techniques.
Possible improvements:
-How do we know that your model is accurate enough. Above 50% shows promise as your model is showing some trend but is the accuracy useful enough to your audience?
-Can we see your errors that you calculated for different amounts of parameters? Shows the reader whether or not you are actually overfitting or underfitting.
-Not too sure the utility of some of your visualizations. The total whiff,take, and swings might not be useful as a whole since we would probably care about individual players instead.