Title: Deep mining of e-commerce consumer behaviour data based on concept hierarchy tree

Authors: Yingchun Han

Addresses: College of Marxism, Heilongjiang Bayi Agricultural University, Daqing, Heilongjiang, 163319, China

Abstract: In order to solve the problems of low data collection efficiency, high noise, and low accuracy in traditional e-commerce consumer behaviour user data mining methods, a deep mining method for e-commerce consumer behaviour data based on concept hierarchy tree is proposed. Use Python scripting language to collect e-commerce consumer behaviour data from e-commerce platforms, and use Myriad filtering algorithm to remove the interference noise in e-commerce consumer behaviour data. Based on non-interference noise free e-commerce consumer behaviour data, utilising domain expert participation and machine learning algorithms, a concept hierarchical tree based e-commerce consumer behaviour data mining model is established to achieve deep mining of e-commerce consumer behaviour data. Experimental results show that the method proposed in this paper collects e-commerce consumer behaviour data more quickly, effectively removes interference noise contained in e-commerce consumer behaviour data, and can effectively and deeply mine the behavioural preferences of e-commerce consumers, with significant applicability.

Keywords: concept hierarchy tree; e-commerce consumer; behaviour data; deep mining; myriad filtering algorithm.

DOI: 10.1504/IJWBC.2024.142476

International Journal of Web Based Communities, 2024 Vol.20 No.3/4, pp.323 - 339

Received: 30 May 2023
Accepted: 10 Oct 2023
Published online: 04 Nov 2024 *