AttentionHR: An Enhanced Transformer-Based Deep Learning Framework for Predicting Employee Turnover in the IT Industry
Keywords:
Employee Turnover Prediction, Transformer, Attention Mechanism, Deep Learning, IT Talent ManagementAbstract
This study proposes AttentionHR, an enhanced Transformer-based deep learning model addressing the increasingly critical talent retention challenge in the IT and Internet industries. The model maps multidimensional employee data—including personal attributes, work status, and organizational environment factors—into a high-dimensional space through feature embedding techniques and incorporates an improved multi-attention mechanism to deeply analyze dynamic feature interactions. Experimental results demonstrate the model's superior performance compared to traditional machine learning methods, achieving 88.16% accuracy. Feature importance analysis reveals that salary level, job satisfaction, and technology stack updating pressure are the three most influential factors affecting IT employee turnover. In practical implementation at an Internet company, the model successfully identified 85% of actual departure cases and reduced turnover rates from 25% to 12% through timely interventions. These findings provide valuable data-driven support for IT companies to formulate targeted talent retention strategies, offering significant theoretical and practical contributions to the intelligent transformation of talent management.
References
Pesce, D. (2023). Unveiling the Determinants of IT Business Value: An Industry-Level Analysis on the Role of the Information-Based Nature of the Product. IEEE Transactions on Engineering Management.
Wei, T., Wang, W., & Yu, S. (2022). Analysis of the Cognitive Load of Employees Working from Home and the Construction of the Telecommuting Experience Balance Model. Sustainability, 14(18), 11722.
Jo, C., Kim, D. H., & Lee, J. W. (2023). Forecasting unemployment and employment: A system dynamics approach. Technological Forecasting and Social Change, 194, 122715.
Li, W. (2023). A transformer-based deep learning framework to predict employee attrition. PeerJ Computer Science, 9, e1570.
Raza, A., Munir, K., Almutairi, M., Younas, F., & Fareed, M. M. S. (2022). Predicting employee attrition using machine learning approaches. Applied Sciences, 12(13), 6424.
Chung, D., Yun, J., Lee, J., & Jeon, Y. (2023). Predictive model of employee attrition based on stacking ensemble learning. Expert Systems with Applications, 215, 119364.
Najafi-Zangeneh, S., Shams-Gharneh, N., Arjomandi-Nezhad, A., & Hashemkhani Zolfani, S. (2021). An improved machine learning-based employees attrition prediction framework with emphasis on feature selection. Mathematics, 9(11), 1226.
Sekaran, K., & Shanmugam, S. (2022). Interpreting the factors of employee attrition using explainable AI. In 2022 International Conference on Decision Aid Sciences and Applications (DASA) (pp. 932-936). IEEE.
Aggarwal, S., Singh, M., Chauhan, S., Sharma, M., & Jain, D. (2022). Employee attrition prediction using machine learning comparative study. In Intelligent Manufacturing and Energy Sustainability: Proceedings of ICIMES 2021 (pp. 453-466). Springer Singapore.
Elsahoryi, N. A., Alathamneh, A., Mahmoud, I., & Hammad, F. (2022). Association of salary and intention to stay with the job satisfaction of the dietitians in Jordan: A cross-sectional study. Health Policy OPEN, 3, 100058.
Manoharan, G., Sharma, P., Chaudhary, V., & Patel, D. (2024). The Future of Work: Examining the Impact of AI/ML on Job roles, Organizational Structures, and Talent Management Practices. Trends in Information Management, 9(1), 45-67. IEEE.
