Please enable JavaScript.
Coggle requires JavaScript to display documents.
Supervised learning (Things that should be communicated during…
Supervised learning
Things that should be communicated during presentation
Areas where the models struggles
Internal vs external data
Model predictive features for model building
When explaining a model directional results tend to make sense
Model quality metrics (confusion matrix)
Feature types especially interesting to management
Features requiring further examination
Immutable features
Features good for modeling, but no value to management in the end
Features that need to be changed and therefore require a re-run of the models
Mutable features
Features management could possibly change
Business problem
Recommended business actions
Before communicating to management
Make sure made no mistakes made in creation process
Can do so by releasing holdout data
Release holdout data by clicking unlock holdout
Then, click on holdout column to re-sort leaderboard by those scores
Best outcome: the models did not change between two sorts
Communicate model insights