A Deep Learning Model Based on Bidirectional Temporal Convolutional Network (Bi-TCN) for Predicting Employee Attrition DOI Creative Commons
Farhad Mortezapour Shiri, Shingo Yamaguchi, Mohd Anuaruddin Bin Ahmadon

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(6), С. 2984 - 2984

Опубликована: Март 10, 2025

Employee attrition, which causes a significant loss for an organization, is the term used to describe natural decline in number of employees organization as result numerous unavoidable events. If company can predict likelihood employee leaving, it take proactive steps address issue. In this study, we introduce deep learning framework based on Bidirectional Temporal Convolutional Network (Bi-TCN) attrition. We conduct extensive experiments two publicly available datasets, including IBM and Kaggle, comparing our model’s performance against classical machine learning, models, state-of-the-art approaches across multiple evaluation metrics. The proposed model yields promising results predicting achieving accuracy rates 89.65% dataset 97.83% Kaggle dataset. also apply fully connected GAN-based data augmentation technique three oversampling methods augment balance show that model, combined with approach, improves 92.17%. applied SHAP method identify key features most significantly influence These findings demonstrate efficacy showcasing its potential use various industries organizations.

Язык: Английский

A Deep Learning Model Based on Bidirectional Temporal Convolutional Network (Bi-TCN) for Predicting Employee Attrition DOI Creative Commons
Farhad Mortezapour Shiri, Shingo Yamaguchi, Mohd Anuaruddin Bin Ahmadon

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(6), С. 2984 - 2984

Опубликована: Март 10, 2025

Employee attrition, which causes a significant loss for an organization, is the term used to describe natural decline in number of employees organization as result numerous unavoidable events. If company can predict likelihood employee leaving, it take proactive steps address issue. In this study, we introduce deep learning framework based on Bidirectional Temporal Convolutional Network (Bi-TCN) attrition. We conduct extensive experiments two publicly available datasets, including IBM and Kaggle, comparing our model’s performance against classical machine learning, models, state-of-the-art approaches across multiple evaluation metrics. The proposed model yields promising results predicting achieving accuracy rates 89.65% dataset 97.83% Kaggle dataset. also apply fully connected GAN-based data augmentation technique three oversampling methods augment balance show that model, combined with approach, improves 92.17%. applied SHAP method identify key features most significantly influence These findings demonstrate efficacy showcasing its potential use various industries organizations.

Язык: Английский

Процитировано

0