Concept Clustering in Design Teams: A Comparison of Human and Machine Clustering

Abstract

Concept clustering is an important element of the product development process. The process of reviewing multiple concepts provides a means of communicating concepts developed by individual team members and by the team as a whole. Clustering, however, can also require arduous iterations and the resulting clusters may not always be useful to the team. In this paper, we present a machine learning approach on natural language descriptions of concepts that enables an automatic means of clustering. Using data from over 1000 concepts generated by student teams in a graduate new product development class, we provide a comparison between the concept clustering performed manually by the student teams and the work automated by a machine learning algorithm. The goal of our machine learning tool is to support design teams in identifying possible areas of “over-clustering” and/or “under-clustering” in order to enhance divergent concept generation processes.

Exploring Machine-based Idea Landscapes – The Impact of Granularity

“…Nevertheless, smaller clusters might also be interesting to research as they entail relatively unique solutions. While our research focused on ideas generated in a crowdsourcing contest, the findings on the impact of granularity in landscape generation are also relevant for other settings where knowledge is explored to identify the best possible solutions, such as allocations of patents or design concepts [32,56].…”

Data-driven design: the new challenges of digitalization on product design and development

“…Cluster analysis, for instance, has been employed with a descriptive purpose both during the planning phase, to distinguish between potential and target customer from a large dataset (Tao et al 2018), and during requirement elicitation (Zhang et al 2017;Shimomura et al 2018). Conjoint analysis has been used, instead, in defining customer preferences and suggesting the possible functions and performances of a new design solution (Song & Kusiak 2009).…”

Data-Driven Design in Concept Development: Systematic Review and Missed Opportunities

“…A different approach was taken by Chowdhery and Bertoni (2018) mining the second-hand online purchase data to set targets for the new machine to be designed. The descriptions of previous product concepts is a frequently used source of data for the generation and selection of new concepts, either through applying mathematical modeling (Zhang et al, 2017), step-forward and path-track (Chen et al, 2019), or text mining . The latter method of analysis is also used by Wodehouse et al (2018) on a database of patents.…”