Configuration design problems are common in everyday life as well as engineering, with examples ranging from the selection and arrangement of furniture for a living room to the type of problem-solving used by NASA engineers to return Apollo 13 safely to Earth. There are many theoretical approaches for solving configuration design problems but few studies have examined how humans naturally solve them. This work used data-mining techniques (specifically hidden Markov models) to study the behavioral patterns shown by humans solving two distinct configuration design problems. Mining this data revealed beneficial process heuristics that are potentially generalizable to the entire class of configuration design problems. The trained models indicate that designers proceed through four procedural states, beginning in a state dominated by topology design and progressing to a final state with a focus on parameter design. The mined models also indicate that high-performing designers opportunistically tune parameters early in the process, enabling a more effective and nuanced search for good solutions.

​Collecting data on user needs can result in overwhelming amounts of data, especially if user groups are large and diverse. Additional analysis is necessary to prioritize a small subset of needs for further consideration. This study presents a simplified quality metric and online interface appropriate to initially screen and prioritize lists exceeding 500 statements for a single topic or product area. Over 20,000 ratings for 1697 need statements across three common product areas were collected in 6 days.  A series of analyses tested whether particular characteristics of users and groups affect the number of high-quality needs that can be generated.  The evaluated characteristics were user group size, needs submitted per person, and expertise and experience levels of users.  The results provided important quantitative evidence of fundamental relationships between the quantity and quality of need statements. Increased quantities of high-quality need statements resulted both due to increasing user group size and due to increasing counts per person using novel content-rich methods to help users articulate needs. However, a user’s topic-specific expertise (self-rated) and experience level (self-rated hours per week) were not significantly associated with increasing need quality.

Lead users play a vital role in next generation product development, as they help designers discover relevant product feature preferences months or even years before they are desired by the general customer base. Existing design methodologies proposed to extract lead user preferences are typically constrained by temporal, geographic, size and heterogeneity limitations. To mitigate these challenges, the authors of this work propose a set of mathematical models that mine social media networks for lead users and the product features that they express relating to specific products.  The authors hypothesize that i) lead users are discoverable from large scale social media networks and ii) product feature preferences, mined from lead user social media data, represent product features that do not currently exist in product offerings but will be desired in future product launches. An automated approach to lead user product feature identification is proposed to identify latent features (product features unknown to the public) from social media data. These latent features then serve as the key to discovering innovative users from the ever increasing pool of social media users. The authors collect  ~2.1 billion social media messages in the United States during a period of 31 months (from March 2011 to September 2013) in order to determine whether lead user preferences are discoverable and relevant to next generation smartphone designs.

For the Abstract and Full Paper please see ASME's Digital Collection.