Trend mining for predictive product design

Conrad S. Tucker, Harrison M. Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The Preference Trend Mining (PTM) algorithm that we propose in this work aims to address some fundamental challenges of current demand modeling techniques being employed in the product design community. The first contribution is a multistage predictive modeling approach that captures changes in consumer preferences (as they relate to product design) over time, hereby enabling design engineers to anticipate next generation product features before they become mainstream/unimportant. Because consumer preferences may exhibit monotonically increasing or decreasing, seasonal or unobservable trends, we proposed employing a statistical trend detection technique to help detect time series attribute patterns. A time series exponential smoothing technique is then used to forecast future attribute trend patterns and generate a demand model that reflects emerging product preferences over time. The second contribution of this work is a novel classification scheme for attributes that have low predictive power and hence may be omitted from a predictive model. We propose classifying such attributes as either obsolete, nonstandard or standard, with the appropriate classification given based on the time series entropy values that an attribute exhibits. By modeling attribute irrelevance, design engineers can determine when to retire certain product features (deemed obsolete) or incorporate others into the actual product architecture (standard) while developing modules for those attributes exhibiting inconsistent patterns throughout time (nonstandard). A cell phone example containing 12 time stamped data sets (January 2009-December 2009) is used to validate the proposed Preference Trend Mining model and compare it to traditional demand modeling techniques for predictive accuracy and ease of model generation.

Original languageEnglish (US)
Title of host publicationASME 2010 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE2010
Pages1007-1021
Number of pages15
EditionPARTS A AND B
DOIs
StatePublished - Dec 1 2010
EventASME 2010 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE2010 - Montreal, QC, Canada
Duration: Aug 15 2010Aug 18 2010

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
NumberPARTS A AND B
Volume1

Other

OtherASME 2010 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE2010
CountryCanada
CityMontreal, QC
Period8/15/108/18/10

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Mechanical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Trend mining for predictive product design'. Together they form a unique fingerprint.

  • Cite this

    Tucker, C. S., & Kim, H. M. (2010). Trend mining for predictive product design. In ASME 2010 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE2010 (PARTS A AND B ed., pp. 1007-1021). (Proceedings of the ASME Design Engineering Technical Conference; Vol. 1, No. PARTS A AND B). https://doi.org/10.1115/DETC2010-28364