Collaborative Research: A Hierarchical Multidimensional Network-based Approach for Multi-Competitor Product Design

本研究的目标是使用基于网络的分层多维设计方法来调查客户考虑的产品以及他们最终购买的产品。基于对工程设计中的社会技术互动进行建模的需要，本研究将设计理论与网络科学相结合，探索了三个相互关联的主题：1)考虑产品关联和社会影响的两阶段多维网络模型；2)预测多竞争者战略决策影响的动态网络模型；3)知识转移，展示泛化能力和共享数据资源的创建，以造福于研究社区。这个项目将推进复杂系统的设计理论，并开发用于在工程设计中模拟社会技术交互作用的定量方法。与企业驱动的设计相结合，开发的方法将增强美国工业在不断变化的市场中的竞争力。测试案例包括电动汽车和小型SUV设计的主要案例研究，以及家用产品设计的次要案例研究。该项目还将培养学生在数据科学、网络科学和人工智能方面的培训，特别强调代表不足的群体、女性和本科生的参与。这项研究的智力价值体现在四个方面。首先，分层网络模型将客户的考虑和选择作为不同的、但集成的行为进行研究。它确定了考虑和选择阶段背后的独特驱动因素。其次，这项研究克服了在客户的社交网络上丢失数据的实际挑战。该解决方案依赖于一种创新的方法来评估个人的偏好如何受到他们自己的以自我为中心的社交联系的影响，方法是通过自动行为者属性模型(ALAAM)与多维客户-产品网络(MCPN)框架的协同集成来评估个人的偏好如何受到他们自己的自我中心社交关系的影响。第三，利用时间指数随机图模型(t-ERGM)，动态网络建模方法将考虑到当前的竞争结构和多个竞争者的设计决策来预测未来的市场竞争。最后，将开发一个基于众包的数据收集平台，集成在线产品数据和评论，以获取客户在多阶段决策中的偏好。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The objective of this research is to investigate what product customers consider and what they eventually purchase using a hierarchical, multidimensional network-based design approach. Motivated by the need to model socio-technical interactions in engineering design, this research combines design theory with network science to explore three interrelated topics: 1) two-stage multidimensional network models for customer preference modeling that consider product associations and social influence; 2) dynamic network models for predicting the impact of multi-competitor strategic decisions, and 3) knowledge transfer to demonstrate generalizability and creation of shared data resources to benefit research community. This project will advance design theories of complex systems and develop quantitative methods for modeling socio-technical interactions in engineering design. Integrated with enterprise-driven design, the methods developed will enhance US industry’s competitiveness within changing markets. The test cases include a primary case study on the design of electric vehicles and small SUVs and a secondary case study on the design of household products. The project will also foster student training in data science, network science and Artificial Intelligence, with particular emphasis on the participation of underrepresented groups, females, and undergraduates.The intellectual merit of this research is manifested in four aspects. First, the hierarchical network model studies customers’ consideration and choice as distinct, but integrated, behaviors. It identifies distinctive driving factors underlying the consideration and choice stages. Second, this research overcomes the practical challenges of missing data on customers' social networks. The solution relies on an innovative approach to assess how individuals’ preferences are influenced by their own egocentric social contacts through a synergistic integration of autologistic actor attribute model (ALAAM) with the Multidimensional Customer-Product Network (MCPN) framework. Third, using temporal Exponential Random Graph Model (t-ERGM), the dynamic network modeling approach will allow the prediction of future market competition considering the present competition structure and multi-competitor design decisions. Finally, a crowdsourcing-based data collection platform integrating online product data and reviews will be developed for eliciting customer preferences in multi-stage decision making.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.