The earner of this badge is able to identify the issues related to using too many predictors (the "curse of dimensionality"); use principal components analysis to reduce the number of predictors to a smaller number of "components" of correlated predictors; use hierarchical clustering and k-means clustering to find and describe clusters of similar records; use association rules to find patterns of "what goes with what" in transaction data; and combine unsupervised and supervised learning methods.