Learning about Shapley values
Several chapters in this book will revisit one method in particular: SHAP. So, it's best that we get an overview now of the mathematical foundation and the properties behind it. We will do this through a basketball analogy.
Imagine you are blindfolded at a basketball game where a loudspeaker announces whenever a player for your team enters or exits the court or the team scores. The loudspeaker won't tell you who scored and you are blindfolded, so you don't know who scored or who even assisted! They only refer to players by number, and you don't know who they are anyway. They could be good players or bad players. At any given time, your best guess would be that whoever last joined had something to do with the latest outcome, whether good or bad. Therefore, over time you start getting a sense of which players correlate the most with the better results and which have the opposite effect or none at all.
What if we were able to simulate...
