A New Under-Sampling Method Using Genetic Algorithm for Imbalanced Data Classification
Jihyun Ha, Jong‐Seok Lee · 2016
The class imbalance problem is frequently found in many real-world domains, where many of traditional classifiers often fail to detect minority class objects due to paying less attention to those. In an effort to address this class imbalance problem, a new under-sampling technique GAUS (genetic algorithm based under-sampling) is proposed in this paper. GAUS is designed to overcome several limitations of existing methods such as performance instability and information loss of data distribution. To select informative majority objects, GAUS tries to maximize the performance of a prototype classifier such that the prototypes minimize the loss between distributions of original and undersampled majority objects. We confirmed the effectiveness of the proposed GAUS based on real-world datasets.