Geometric SMOTE for imbalanced datasets with nominal and continuous features

@article{fonseca2023geometric,
  author = {Fonseca, Joao and Bacao, Fernando},
  title = {Geometric SMOTE for imbalanced datasets with nominal and continuous features},
  journal = {Expert Systems with Applications},
  year = {2023},
  volume = {234},
  pages = {121053},
  doi = {https://doi.org/10.1016/j.eswa.2023.121053},
  url = {https://www.sciencedirect.com/science/article/pii/S0957417423015555},
  abstract = {Imbalanced learning can be addressed in 3 different ways: Resampling, algorithmic modifications and cost-sensitive solutions. Resampling, and specifically oversampling, are more general approaches when opposed to algorithmic and cost-sensitive methods. Since the proposal of the Synthetic Minority Oversampling TEchnique (SMOTE), various SMOTE variants and neural network-based oversampling methods have been developed. However, the options to oversample datasets with nominal and continuous features are limited. We propose Geometric SMOTE for Nominal and Continuous features (G-SMOTENC), based on a combination of G-SMOTE and SMOTENC. Our method modifies SMOTENC’s encoding and generation mechanism for nominal features while using G-SMOTE’s data selection mechanism to determine the center observation and k-nearest neighbors and generation mechanism for continuous features. G-SMOTENC’s performance is compared against SMOTENC’s along with two other baseline methods, a State-of-the-art oversampling method and no oversampling. The experiment was performed over 20 datasets with varying imbalance ratios, number of metric and non-metric features and target classes. We found a significant improvement in classification performance when using G-SMOTENC as the oversampling method. An open-source implementation of G-SMOTENC is made available in the Python programming language.},
  issn = {0957-4174},
  keywords = {Imbalanced learning, Oversampling, SMOTE, Data generation, Nominal data}
}