# How to make Random Forests more interpretable?

Are there any methods that one could utilize to make Random Forest more interpretable? Random Forest performs much better than CART but it is a lot less interpretable.

• Did you take a look at the random-forest tag? In particular, this question and the accepted answer may be of interest to you: Obtaining knowledge from a random forest. – chl Jul 11 '12 at 18:49
• A recent article in JCGS suggests a novel approach for visualizing relationships between predictors in random forests named Partition Maps (Meinshausen, 2011, pre-print PDF here. He also has an R package for the graphs on his website. – Andy W Jul 11 '12 at 20:18
• @AndyW (+1) Thanks for sharing those references. – chl Jul 11 '12 at 20:22
• This is just... wrong. The core idea behind ML is that models are black boxes, thus looking inside will always be either deceiving or disappointing. – mbq Jul 11 '12 at 20:46
• @mbq My knowledge is quite limited, but this is ... a very strong statement. If one finds certain features to be useful for predicting a certain outcome both on the validation set AND in live application, these features contain useful information. Period. It may be that the data is flawed and it performed well just by accident or only in this specific case, but it gives you hints. Compare this hints across several projects in the same domain and one get's some sort of domain knowledge. – steffen Jul 16 '12 at 11:53

• The first sentence is really on the point. Frank Harrell mentioned in a comment on this site something like $n>10,000$ to get stable results, if I remember correctly. The variable importance measures are often used for feature selection in wrapper or embedded methods, though. Maybe you want to elaborate on where difficulties with interpretation arise? – chl Jul 11 '12 at 20:20
• The Random forest algorithm is an ensemble method which uses random sampling of cases (bootstrap) and variables (mtry parameter). The out-of-bag sample is used to derive a measure of variable importance (using a permutation technique) and assess cases proximities through a voting process (number of times two individual ended up in the same leave divided by the number of trees). Viewed as a black box, I don't think RF yields such an easy interpretation (yet it outperforms many competive algorithms which are easier to decipher). – chl Jul 11 '12 at 20:01