Data augmentation and resampling techniques
Class imbalance is a common issue in datasets with rare events. Class imbalance can adversely affect the model’s performance, as the model tends to be biased toward the majority class. To address this, we will explore two resampling techniques:
- Oversampling: Increasing the number of instances in the minority class by generating synthetic samples
- Undersampling: Reducing the number of instances in the majority class to balance class distribution
Let’s discuss these resampling techniques in more detail.
Oversampling using SMOTE
Synthetic Minority Over-sampling TEchnique (SMOTE) is a widely used resampling method for addressing class imbalance in machine learning datasets, especially when dealing with rare events or minority classes. SMOTE helps to generate synthetic samples for the minority class by interpolating between existing minority class samples. This technique aims to balance class distribution...
