Social e-commerce consumer behaviour prediction model based on hierarchical polarisation characteristics

In this paper, a social e-commerce consumer behaviour prediction model based on layered polarisation characteristics is constructed. Consumer characteristics, product characteristics and interaction features are the three aspects used to construct the social electricity consumer behaviour prediction index system; with the improved locally linear embedding method for social electricity consumer behaviour predictors of high-dimensional data dimension used to reduce processing. According to the hierarchical polarisation characteristics, social electricity consumer behaviour prediction index weight calculation was based on the weight coefficient to construct the complete prediction model of social e-commerce consumer behaviour based on the characteristics of stratified polarisation. The simulation results show that the established model can predict the consumer behaviour of social e-commerce with high accuracy and short prediction time. Copyright © 2022 Inderscience Enterprises Ltd.