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

2017 ◽  
Vol 139 (11) ◽  
Author(s):  
Chengwei Zhang ◽  
Youngwook Paul Kwon ◽  
Julia Kramer ◽  
Euiyoung Kim ◽  
Alice M. Agogino
Keyword(s):  
Machine Learning ◽  
Product Development ◽  
New Product Development ◽  
Learning Algorithm ◽  
Product Development Process ◽  
Design Teams ◽  
Concept Generation ◽  
Support Design ◽  
Concept Clustering ◽  
Student Teams

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.

Deep Learning for Design in Concept Clustering

2017 ◽  
Author(s):  
Chengwei Zhang ◽  
Youngwook Paul Kwon ◽  
Julia Kramer ◽  
Euiyoung Kim ◽  
Alice M. Agogino
Keyword(s):  
Machine Learning ◽  
Product Development ◽  
New Product Development ◽  
Learning Algorithm ◽  
Product Development Process ◽  
Concept Generation ◽  
Support Design ◽  
Team Members ◽  
Concept Clustering ◽  
Student Teams

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 1,000 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.

Evaluating the Discriminatory Value and Reliability of Ideation Metrics for Their Application to Concept Development and Prototyping

2017 ◽  
Author(s):  
Jessica Menold ◽  
Kathryn Jablokow ◽  
Timothy Simpson ◽  
Rafael Seuro
Keyword(s):  
Product Development ◽  
New Product Development ◽  
New Product ◽  
Concept Development ◽  
Product Development Process ◽  
Concept Generation ◽  
Market Place ◽  
Design Changes ◽  
The Impact ◽  
Original Concept

Approximately half of new product development projects fail in the market place. Within the product development process, prototyping represents the largest sunk cost; it also remains the least researched and understood. While researchers have recently started to evaluate the impact of formalized prototyping methods and frameworks on end designs, these studies have typically evaluated the success or failure of these methods using binary metrics, and they often evaluate only the design’s technical feasibility. Intuitively, we know that a product’s success or failure in the marketplace is determined by far more than just the product’s technical quality; and yet, we have no clear way of evaluating the design changes and pivots that occur during concept development and prototyping activities, as an explicit set of rigorous and informative metrics to evaluate ideas after concept selection does not exist. The purpose of the current study was to investigate the discriminatory value and reliability of ideation metrics originally developed for concept generation as metrics to evaluate functional prototypes and related concepts developed throughout prototyping activities. Our investigation revealed that new metrics are needed in order to understand the translation of product characteristics, such as originality, novelty, and quality, from original concept through concept development and prototyping to finalized product.

Applying Design Roadmapping in New Product Development Education: Insights From Student Design Teams

2018 ◽  
Author(s):  
Euiyoung Kim ◽  
Sara L. Beckman ◽  
Alice M. Agogino
Keyword(s):  
Product Development ◽  
New Product Development ◽  
New Product ◽  
Design Teams ◽  
Experience Design ◽  
Development Education ◽  
User Experience Design ◽  
Student Teams ◽  
Survey Responses ◽  
The University

A design roadmap is a canvas that facilitates embedding user experience design goals into the earliest stages of the design process by envisioning how a concept can evolve over time to meet changing user needs. This paper explores the development of design roadmap canvases by product design teams in an educational setting. It does so by (1) examining the design roadmapping workshop deliverables from new product development student teams at the University of California, Berkeley between 2014–2017 and (2) analyzing 107 survey responses from students in those workshops about their design roadmapping experiences. The paper describes the benefits to students using design roadmapping and insights into how best to engage students in design roadmapping exercises. Finally, based on the challenges students had with the process employed in the experiment, recommendations are provided to help educators and practitioners make productive use of design roadmaps.

New methodology for product development process using structured tools

2020 ◽  
pp. 095440542097122
Author(s):  
Carlos Relvas ◽  
António Ramos
Keyword(s):  
Product Development ◽  
New Product Development ◽  
Development Process ◽  
New Product ◽  
Development Cooperation ◽  
Product Development Process ◽  
Concept Generation ◽  
Systematic Method ◽  
Development Team ◽  
Future Developments

The product development is a multidisciplinary process but also involves different areas of knowledge ranging from creativity in concept generation to refinement of design and finally the validation of the product. There are different approaches that attempt to define the best product development process, and thereby establishes a reliable method for efficiently transforming ideas into products. The use of a method that systematically establishes a work process seems to be highly advantageous, not only because it defines a critical and guiding path of work, organizing the tasks and their results, but also facilitates the communication of the development team. The methodology can provide records and other graphic documents that allow the development team to access these for future developments. The work presented here is the development of a systematic method supported by the use of structured tools to support the decisions, data processing and transposition of the same to the project in the approach to the new Product Development process. This research methodology was introduced and already implemented in projects at Department of Mechanical Engineering, University of Aveiro. The work developed on it, both at the level of the students’ project and in the work of Development cooperation with companies presented good results. This method result in a structured way to transforming ideas into products.

Advantages of Time-Based New Product Development in a Fast-Cycle Industry

1997 ◽  
Vol 34 (1) ◽  
pp. 36-49 ◽  
Author(s):  
Srikant Datar ◽  
C. Clark Jordan ◽  
Sunder Kekre ◽  
Surendra Rajiv ◽  
Kannan Srinivasan
Keyword(s):  
Product Development ◽  
New Product Development ◽  
Market Share ◽  
Lead Time ◽  
Development Process ◽  
New Product ◽  
Product Development Process ◽  
Concept Generation ◽  
Volume Production ◽  
The Impact

The authors study the impact of time-based product development on sustainable market share gains in a high-technology computer component industry. Three dominant firms, with international new product development and manufacturing facilities, have introduced more than 200 new products into this fast-cycle market in a five-year period. The authors systematically examine the leads and lags at critical stages of the product development process: concept generation, prototype completion, and volume production. Their main finding is that lead-time advantage affects market share positively, albeit differentially, at each stage. The benefit of lead-time gain is greatest at the volume production stage, followed by the concept generation stage. The authors also develop a new notion of lead-time threshold—a time period in which if a competitor catches up, no market share gain is achieved by the firm that introduces the product first. They endogenously estimate the magnitude of the threshold for each stage of the product development process, observing that a significant threshold is present at both the concept generation and volume production stages. Finally, the structure of the development process, which differs across the firms in the market, affords significant differential ability to catch up with competitors.

Reliability and Accuracy of Bootstrap and Monte Carlo Methods for Demand Distribution Modeling

2011 ◽  
Author(s):  
Swithin S. Razu ◽  
Shun Takai
Keyword(s):  
Monte Carlo ◽  
Product Development ◽  
Conjoint Analysis ◽  
New Product Development ◽  
Demand Uncertainty ◽  
New Product ◽  
Product Development Process ◽  
Choice Data ◽  
Product Concept ◽  
Demand Distribution

Estimation of demand is one of the most important tasks in new product development. How customers come to appreciate and decide to purchase a new product impacts demand and hence profit of the product. Unfortunately, when designers select a new product concept early in the product development process, the future demand of the new product is not known. Conjoint analysis is a statistical method that has been used to estimate a demand of a new product concept from customer survey data. Although conjoint analysis has been increasingly incorporated in design engineering as a method to estimate a demand of a new product design, it has not been fully employed to model demand uncertainty. This paper demonstrates and compares two approaches that use conjoint analysis data to model demand uncertainty: bootstrap of respondent choice data and Monte Carlo simulation of utility estimation errors. Reliability of demand distribution and accuracy of demand estimation are compared for the two approaches in an illustrative example.

Sign in / Sign up

Export Citation Format

Share Document