Benefit-based consumer segmentation and performance evaluation of clustering approaches: An evidence of data-driven decision-making

作者：

Highlights：

• Performance of different clustering techniques varies significantly in practice.

• Generalised-distance and Grower-distance metrics perform better for ordinal data.

• Fuzzy and Self-Organising Maps (SOM) techniques are comparatively more efficient.

• Consumer segments derived from SOM has more capability to provide useful insights.

摘要

•Performance of different clustering techniques varies significantly in practice.•Generalised-distance and Grower-distance metrics perform better for ordinal data.•Fuzzy and Self-Organising Maps (SOM) techniques are comparatively more efficient.•Consumer segments derived from SOM has more capability to provide useful insights.

论文关键词：Big Data Analytics,Data visualisation,Consumer segmentation,Cluster analysis,Business intelligence,Data-driven decisions

论文评审过程：Received 30 April 2017, Revised 28 February 2018, Accepted 6 March 2018, Available online 9 March 2018, Version of Record 29 July 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.03.007