Authors: Kyungdoh Kim; Seokcheon Lee; Gavriel Salvendy
Addresses: Department of Industrial Engineering, Hongik University, Seoul, 04066, South Korea ' School of Industrial Engineering, Purdue University, West Lafayette, IN, 47906, USA ' Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, 32816, USA
Abstract: In new product or service development, design alternatives are generally evaluated by subjective rating, and the one with the highest average score is often chosen. However, the public might not prefer an alternative as much as its average rating suggests. The main objective of this study is to examine the possibility of identifying a predictive function that can accurately represent the products that most people want to purchase in the context of mobile phone products. This paper introduces social welfare functions for developing predictive functions and several metrics to evaluate the functions. Two case studies were performed to determine predictive function for mobile phones. In both case studies, the Atkinson welfare function with a parameter value of 2.5 predicted subjects' purchase decisions and market sales the most. The commonly used average function was not as good as the Atkinson function.
Keywords: design evaluation; social utility; mobile phone; predictive function; atkinson function; market share.
International Journal of Mobile Communications, 2019 Vol.17 No.3, pp.376 - 389
Accepted: 23 Dec 2017
Published online: 21 Feb 2019 *