KOREASCHOLAR

TabTransformer와 조건부 GAN 알고리즘을 활용한 우리나라 대졸자 취업 만족도 예측 모델의 개선을 위한 데이터 증강 기법 연구 Applying TabTransformer and Conditional GAN Algorithms for Enhancing Job Satisfaction Prediction of South Korean College Graduates

변해원
  • 언어ENG
  • URLhttp://db.koreascholar.com/Article/Detail/437759
PDF 원문보기
한국기계기술학회지 (韓國機械技術學會誌)
제26권 제5호 (2024.10)
pp.828-839
한국기계기술학회 (Korean Society of Mechanical Technology)
초록

This study integrates TabTransformer and CTGAN for predicting job satisfaction among South Korean college graduates. TabTransformer handles complex tabular data relationships with self-attention, while CTGAN generates high-quality synthetic samples. The combined approach achieves an accuracy of 0.85, precision of 0.83, recall of 0.82, F1-score of 0.82, and an AUC of 0.88. Cross-validation confirms the model's robustness and generalizability with a mean accuracy of 0.85 and a standard deviation of 0.008. The integration of TabTransformer and CTGAN enhances predictive accuracy and model generalizability, providing valuable insights for employment policy and research.

키워드
직무 만족도탭트랜스포머조건부 생성적 적대 신경망데이터 증강멀티헤드 어텐션 Job SatisfactionTabTransformerConditional GANData AugmentationMulti-Head Attention
목차
Abstract
1. Introduction
2. Related works
3. Materials and Methods
    3.1. Data Preparation
    3.2. Feature Extraction using TabTransformer
    3.3. Data Augmentation using CTGAN
    3.4. Model Training with Augmented Data
    3.5. Final Classification Model Constructionand Evaluation
    3.6. Dataset
4. Results and PerformanceEvaluation
    4.1. Experimental Setup
    4.2 Evaluation Metrics
    4.3. Experimental Results
    4.4. Accuracy
    4.5. Precision
    4.6. Recall
    4.7. F1-score
    4.8. Area Under the ROC Curve (AUC)
    4.9. Cross-Validation
5. Discussion
6. Conclusions
References
저자
  • 변해원(Department of AI-Software, Inje University, South Korea) | Haewon Byeon Corresponding author