원문정보
초록
영어
Handling imbalanced datasets in binary classification, especially in employment big data, is challenging. Traditional methods like oversampling and undersampling have limitations. This paper integrates TabNet and Generative Adversarial Networks (GANs) to address class imbalance. The generator creates synthetic samples for the minority class, and the discriminator, using TabNet, ensures authenticity. Evaluations on benchmark datasets show significant improvements in accuracy, precision, recall, and F1-score for the minority class, outperforming traditional methods. This integration offers a robust solution for imbalanced datasets in employment big data, leading to fairer and more effective predictive models.
목차
1. Introduction
2. Materials and Methods
2.1 Imbalance Ratio(IR)
2.2 Generative Adversarial Network (GAN)
2.3 Conditional GAN (CGAN)
2.4 TabNet
2.5 Integration of TabNet and GAN for Imbalanced Data
2.6 Evaluation Metrics
2.7 Experiments
2.8 Logistic Regression (LR)
2.9 Linear Discriminant Analysis (LDA)
2.10 Random Forest (RF)
2.11 Extreme Learning Machines (ELM)
2.12 Hyperparameters and Evaluation
2.13 Data Source
3. Results
3.1 Imvalance Ratio (IR) Analysis
3.2 Performance of the TabNet-Driven GAN Model
3.3 Comparison with Traditional Methods
3.4 Impact of Synthetic Data Generation
3.5 Hyperparameter Tuning and Model Training
4. Conclusion
References