DDSC-SMOTE: an imbalanced data oversampling algorithm based on data distribution and spectral clustering

• Published in: The Journal of supercomputing Vol. 80; no. 12; pp. 17760 - 17789
• Main Authors: Li, Xinqi, Liu, Qicheng
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.08.2024; Springer Nature B.V
• Subjects: Accuracy; Adaptive sampling; Algorithms; Bank fraud; Classification; Clustering; Compilers; Computer Science; Datasets; Interpreters; Machine learning; Noise; Oversampling; Processor Architectures; Programming Languages; Imbalanced data; Spectral clustering; SMOTE; Oversampling; Data preprocessing
• ISSN: 0920-8542; 1573-0484
• DOI: 10.1007/s11227-024-06132-7

Imbalanced data poses a significant challenge in machine learning, as conventional classification algorithms often prioritize majority class samples, while accurately classifying minority class samples is more crucial. The synthetic minority oversampling technique (SMOTE) represents one of the most renowned methods for handling imbalanced data. However, both SMOTE and its variants have limitations due to their insufficient consideration of data distribution, leading to the generation of incorrect and unnecessary samples. This paper, therefore, introduces a novel oversampling algorithm called data distribution and spectral clustering-based SMOTE (DDSC-SMOTE). This algorithm addresses the shortcomings of SMOTE by introducing three innovative data distribution-based improvement strategies: adaptive allocation of synthetic sample quantities strategy, seed sample adaptive selection strategy, and synthetic sample improvement strategy. First, we use the k -nearest neighbor sample labels and the local outlier factor algorithm to remove noisy and outlier samples. Next, we leverage spectral clustering to identify clusters within the minority class and propose a dual-weight factor that considers inter-cluster and intra-cluster distances to allocate the number of synthetic samples effectively, addressing interclass and intraclass imbalances. Furthermore, we introduce a relative position weight coefficient to determine the probability of selecting seed samples within the subcluster, ensuring that important minority samples have higher chances of being sampled. Finally, we improve the SMOTE sample synthesis formula for safer generation. Extensive comparisons on real datasets from the UCI repository demonstrate that DDSC-SMOTE outperforms seven state-of-the-art oversampling algorithms significantly in terms of G -mean and F 1-score, presenting a data distribution-focused solution for addressing imbalanced data challenges.