Editorial
Team structure optimization and talent flow prediction based on graph neural network
@ARTICLE{10.4108/eetsis.11146, author={Shuangshuang Chen and Huaqiang Lai}, title={Team structure optimization and talent flow prediction based on graph neural network}, journal={EAI Endorsed Transactions on Scalable Information Systems}, volume={12}, number={9}, publisher={EAI}, journal_a={SIS}, year={2026}, month={5}, keywords={graph neural network, co-simulation, optimization of team structure, talent flow forecasting, organizational management, Attention mechanism}, doi={10.4108/eetsis.11146} }- Shuangshuang Chen
Huaqiang Lai
Year: 2026
Team structure optimization and talent flow prediction based on graph neural network
SIS
EAI
DOI: 10.4108/eetsis.11146
Abstract
This paper proposes a graph neural network-based framework for team structure optimization and talent flow prediction to address the limitations of traditional methods in modeling complex organizational dynamics. By constructing an organizational graph structure containing 12,547 employees and 56,892 flow records, we develop a hybrid model combining graph attention networks and multi-layer perceptrons to accurately capture team collaboration relationships and talent mobility patterns. The proposed method achieves an F1 score of 78.6% in teamwork prediction, and 81.2% accuracy with 0.864 AUC in talent flow prediction, outperforming traditional methods by over 10%. Experimental results demonstrate that graph neural networks can effectively model complex dependencies in organizational structures, providing data-driven decision support for team optimization and talent management.
