Learning under Localized Minority Imbalance
A tree-based stratified approach that recursively partitions the feature space with the goal of reducing within-stratum LMI distortion, and introduces a gold-standard evaluation protocol that uses unbiased test sets and demonstrates that conventional hold-out evaluation from the same LMI-biased data can substantially m...
Amin Hosseininasab, Steven M. Shugan
· 0 citations