|
Abstract:
|
General regression and classification models are constructed as linear combinations of simple rules derived from data. These rule ensembles are shown to produce predictive accuracy comparable to the best methods. However, their principal advantage lies in interpretation. Each rule is easy to understand, as is its influence on the predictive model. Similarly, the degree of relevance of each of the input variables can be assessed globally, locally in different regions of the input space, or at individual prediction points. Techniques are presented for automatically identifying those variables involved in interactions with other variables, the strength and degree of those interactions, and the identities of the other variables with which they interact. Graphical representations are used to visualize both main and interaction effects.
|
