A Bayesian based approach for analyzing customer’s online sales data to identify weights of product attributes

作者：

Highlights：

• Bayesian inference algorithm is performed to obtain weights of product attributes.

• Kernel density estimation is used to estimate distributions of attribute scores.

• Effect of product attribute on customer satisfaction is obtained via online ratings.

• The applicability of method is demonstrated within a case study.

• The method can be applied to any decision making problem with overall scores.

摘要

•Bayesian inference algorithm is performed to obtain weights of product attributes.•Kernel density estimation is used to estimate distributions of attribute scores.•Effect of product attribute on customer satisfaction is obtained via online ratings.•The applicability of method is demonstrated within a case study.•The method can be applied to any decision making problem with overall scores.

论文关键词：Attribute weighting,Customer satisfaction,Bayesian inference,Markov Chain Monte Carlo,Online ratings

论文评审过程：Received 18 September 2021, Revised 31 July 2022, Accepted 4 August 2022, Available online 9 August 2022, Version of Record 22 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118440