Clustering Product Development Project Organization From the Perspective of Social Network Analysis

Abstract

In product development (PD) organizations, coordinating technical dependencies among teams with different expertise in overlapping processes is a fundamental challenge. This article takes a more sophisticated approach than prior methodologies to improve coordination via organizational clustering, by accounting for both team structural and attribute similarity from the perspective of social network analysis. We built models to quantify the impact of the overlapping processes on the interaction strength among PD teams, which we then used to construct structural similarity by combining tie strength and social cohesion among teams via the design structure matrix. To evaluate the organization network, we propose social embeddedness-related centrality indices within (intracluster) and across (intercluster) team groupings. To facilitate knowledge sharing, we base team attribute similarity on product-and process-related expertise among teams. We integrate the modularity index and an improved silhouette index to find an optimal number of clusters, which we then incorporate with team similarity measures as inputs to a spectral clustering algorithm. An industrial example illustrates the proposed model. The clustering results reinforce several managerial practices but also yield new insights, such as how to measure similarity among teams based on organizational network characteristics and how structural and attribute similarities impact the optimal organizational structure.

Healthcare Operations and Black Swan Event for COVID-19 Pandemic: A Predictive Analytics

“…In this article, univariate prediction models are developed for forecasting new and active COVID cases daily by considering them as two different series and multivariate prediction models considering both the series viz., new and active COVID cases together [82]. Though autocorrelation due to temporal heterogeneity occurs in the time series of both new and active corona-positive cases over the observation period, the degree of autocorrelation varies across the time.…”

Creating Strategies for Enhancing Complex New Product Development: Cluster Analysis of DEA Results

“…Their results indicate that their method can reduce an organization's complexity and thus lead to better results. Yang et al (2019) also approached product development through clustering based on social cohesion among teams based on Social Network Analysis.…”

Design Structure Matrix and Its Applications in Innovation Management

“…Using a clustering method, Yang et al (2019) presented an innovative method to address two critical issues in PD organizational design: how to quantify structural and attribute similarities between PD teams from a social network perspective, and how to identify clusters based on these similarities. They have provided a framework that enables managers to optimize PD organizational architecture more effectively.…”