StatSim → Select

All-relevant feature selection with Boruta.js

Feature selection methods identify important variables in a dataset. Many of those methods search for a minimal feature subset that can be used to predict a target variable well. When you want to understand relationships between variables, it's more important to select all relevant variables, not just the minimal set. Boruta (Kursa, Rudnicki 2010) is one of the most advanced method for such all-relevant feature selection. We ported the original Boruta algorithm to JavaScript so you can use it here without installing R or sending data to a server. All processing happens in the browser, on your local machine.