Importance-performance analysis (IPA) is a technique to  
understand customer satisfaction and improve the quality of  
product attributes. This paper proposes an explainable deep neural  
network (DNN)-based method to conduct the IPA of product  
attributes from online reviews for product design. Previous  
works used shallow neural network (SNN)-based methods to estimate  
importance values. It is unclear whether the SNN is the  
optimal neural network architecture, and the estimated importance  
also has a high variability by a single neural network from  
a training set selected randomly. However, the proposed method  
provides reliable and constant importance values by improving  
the importance estimation of each product attribute in the IPA.  
The proposed method first identifies product attributes and estimates  
their performance, then infers importance values by combining  
explanations of input features from multiple optimal neural  
networks. A case study of smartphones is used to demonstrate  
the proposed method.


Importance-Performance Analysis of Product Attributes Using Explainable Deep Neural Network From Online Reviews

Division / Sponsors: 
Design Engineering Division and Computers & Information In Engineering Division


Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2020/volume/83907

IDETC2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.