Analyzing Online Shopping Behaviors via a new Data-Driven Hesitant Fuzzy Approach

Loading...
Thumbnail Image

Date

2021

Journal Title

Journal ISSN

Volume Title

Publisher

Atlantis Press [Commercial Publisher]

Access Rights

Abstract

Understanding online shopping behaviors is crucial for the survival of many firms. Modeling the customers' online shopping behaviors is a complex problem that involves uncertainty, hesitancy, and imprecision since different generations have different attitudes toward e-commerce. In this study, a new data-driven, hesitant fuzzy cognitive map methodology evaluates the different generations', namely, generations X, Y, and Z, online shopping behaviors. The model is constructed based on the technology acceptance model, diffusion of innovation theory, and extended unified theory of acceptance and technology use. The relations and the level of relations among the parameters are defined by using a data-driven approach. Utilizing a statistical approach enables us to define the relations among the parameters and customer behaviors better. The study's objective is to reveal the impact of different conditions on the customers' online shopping behaviors and help the decision-makers with their online shopping strategies. The statistical model has limitations since it does not reflect the hesitancy and imprecision inherent in customers' online shopping behaviors. We utilize hesitant fuzzy cognitive maps to reflect uncertainty and hesitancy and analyze different scenarios with this map. Different cognitive maps and three scenarios are developed for every generation type, and the customer behaviors are observed through these hesitant fuzzy cognitive maps. (C) 2021 The Authors. Published by Atlantis Press B.V.

Description

Keywords

Online shopping, Customer behavior, Generation cohort, Hesitant fuzzy cognitive mapping, Partial least squares structural equation modeling

Journal or Series

WoS Q Value

Q1

Scopus Q Value

Q1

Volume

Issue

Citation

International Journal of Computational Intelligence Systems Vol. 14(1), 2021, pp. 847–858