Comparing Utility-Based and Network-Based Approaches in Modeling Customer Preferences for Engineering Design

DS 94: Proceedings of the Design Society: 22nd International Conference on Engineering Design (ICED19)

Year: 2019
Editor: Wartzack, Sandro; Schleich, Benjamin; Gon
Author: Sha, Zhenghui (2); Bi, Youyi (1); Wang, Mingxian (3); Stathopoulos, Amanda (1); Contractor, Noshir (1); Fu, Yan (3); Chen, Wei (1)
Series: ICED
Institution: Northwestern University
Section: User-centred design
DOI number: https://doi.org/10.1017/dsi.2019.390
ISSN: 2220-4342

Abstract

Customer preference modeling provides quantitative assessment of the effects of engineering design attributes on customers? choices. Utility-based approaches, such as discrete choice model (DCM), and network analysis approaches, such as exponential random graph model (ERGM), have been developed for customer preference modeling. However, no studies have compared these two approaches. Our objective is to identify the distinctions and connections between these two approaches based on both the theoretical foundation and the empirical evidence. Using the vehicle preference modeling as an example, our study shows that when network structure effects are not considered, results from ERGM are consistent with DCM in most of the test cases. However, in one case where customers have varying choice set with multiple alternatives, inconsistencies are observed, possibly due to the discrepancies of the two models in taking different information when calculating choice probabilities. The insights will lead to valuable guidance for choosing the technique for customer preference modeling and co-developing the two frameworks to support engineering design.

Keywords: Market implications, User centred design, Big data, Network modeling, Customer preference modeling

Download

Please sign in to your account

This site uses cookies and other tracking technologies to assist with navigation and your ability to provide feedback, analyse your use of our products and services, assist with our promotional and marketing efforts, and provide content from third parties. Privacy Policy.