In this section, we're going to take the predictions from a machine learning model, and use those predictions as our outcome variables. Then we will use the original predictors to understand what's going on, that is, the logic behind the machine learning model.
Previously, we saw that we could use different graphs and tables to figure out how to look at relationships between just one variable, one predictor and how it relates to an outcome variable, which is useful and important information to have. But generally, a model uses many variables at the same time. Hence looking at one predictor is useful, but it doesn't exactly give us a complete picture.
Another technique would be to use a decision tree model to help us understand the logic behind a neural net model, or any kind of machine learning model.
Here...
