Integrating persistence process into the analysis of technology convergence using STERGM

Abstract

Understanding the dynamics of technology convergence is indispensable for both academic and industrial perspectives. Traditional analyses have mainly focused on the link formation process, overlooking the role that persistence process plays in shaping technology networks. This paper endeavors to fill this gap by incorporating the persistence process into the analysis of technology convergence using the Separate Temporal Exponential Random Graph Model (STERGM). Utilizing a decade-long dataset of breast cancer drug patents, we provide a comprehensive view of technology convergence mechanisms and their predictive capabilities. Our findings reveal significant differences in network effects between formation and persistence processes, indicating that focusing on only one may misrepresent the evolution of technology networks. The combined model achieves an F1 score of 69.54% in empirical forecasting, confirming its practical utility. Additionally, we introduce Intensification Networks to examine how existing ties strengthen or weaken over time, uncovering the critical role of intensification in the long-term evolution of technology convergence. By capturing both the formation of new ties and the intensification of existing ones, our model offers a more nuanced and forward-looking understanding of convergence dynamics, particularly in identifying potential areas for future technology convergence.