An approach based on the SIR epidemic model and a genetic algorithm for optimizing product feature combinations in feature fatigue analysis

作者：Wu, Mingxing; Wang, Liya^*; Li, Ming; Long, Huijun

来源：Journal of Intelligent Manufacturing, 2015, 26(1): 199-209.

DOI：10.1007/s10845-013-0773-7

• Feature fatigue
• SIR epidemic model
• Genetic algorithm
• Feature combinations optimization

Integrating more features into one product makes the product more attractive, thereby increasing the product's initial sales; however, after having worked with the high-feature product, customers become dissatisfied with the usability problems caused by too many features. This phenomenon is called "feature fatigue". Feature fatigue will lead to negative Word-Of-Mouth, which damages the brand's long-term profit and ultimately decreases the manufacturer's customer equity (CE). To alleviate feature fatigue, it is imperative for designers to decide what features should be integrated to balance initial revenue and long-term profit so as to maximize CE. In this paper, a novel approach based on the SIR epidemic model and a genetic algorithm is proposed to help designers find an optimal feature combination that maximizes CE. Firstly, the SIR epidemic model is utilized to analyze customer purchase behavior under different feature combinations. CE can thus be calculated according to customer purchase analysis. Then a genetic algorithm is adopted to search an optimal feature combination, in which CE is used as the fitness function. Finally, a case example is illustrated to prove the effectiveness of the proposed approach.

• 出版日期2015-2
• 单位上海交通大学