Explainable Outlier Detection Through Decision Tree Conditioning

Will try to fit decision trees that try to "predict" values for each column based on the values of each other column. Along the way, each time a split is evaluated, it will take the observations that fall into each branch as a homogeneous cluster in which it will search for outliers in the 1-d distribution of the column being predicted. Outliers are determined according to confidence intervals in this 1-d distribution, and need to have a large gap with respect to the next observation in sorted order to be flagged as outliers. Since outliers are searched for in a decision tree branch, it will know the conditions that make it a rare observation compared to others that meet the same conditions, and the conditions will always be correlated with the target variable (as it's being predicted from them). Full procedure is described in Cortes (2020) . Loosely based on the 'GritBot' < https://www.rulequest.com/gritbot-info.html> software.


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


1.7.1 by David Cortes, a month ago


Report a bug at https://github.com/david-cortes/outliertree/issues

Browse source code at https://github.com/cran/outliertree

Authors: David Cortes

Documentation:   PDF Manual  

GPL (>= 3) license

Imports Rcpp

Linking to Rcpp, Rcereal

Suggested by isotree.

See at CRAN