Data Mining Algorithm for Demand Forecast Analysis on Flash Sales Platform

Abstract

With the development of the digital economy, the emerging marketing strategy of the e-commerce flash sales has been changing the traditional purchasing habits of customers. This imposes new decision-making challenges for companies involved in flash sales. It is important for companies to build the accurate product demand forecast analysis focusing on the characteristics of the flash sales and customer behaviors. In this paper, VIPS (Weipinhui, a Chinese e-commerce platform) is taken as a case study with the key focus on how sentiment factors in customer reviews affect product demand in flash sale platforms. The paper adopts two sentiment analysis methods based on emotional dictionaries. The method with a higher evaluation index is adopted to integrate the emotional factors into the autoregressive model for product demand and assessment. The experiments prove that the autoregressive model for integrating the sentiment factors demonstrates better forecasting performances than the models without sentiment factors. The experiments further confirm that when product demand for the previous two weeks and customer review sentiment factors in the previous week are taken into consideration, demand forecast effects are most accurate.

Enhancing Community E-Commerce Repurchase Prediction Through Information Entropy Analysis

“…At this stage, information search and online comments have become the focus of attention, which can be matched to consumers' potential search needs in marketing (Attia et al, 2023). M. Zhang et al (2021) aimed at the problem of poor recommendation quality in the case of sparse data, and this paper proposes a recommendation algorithm for sparse data by optimizing the filling of scoring vacancies and considering the number of common scoring items. The effect of the model is more obvious with the increase of data sparsity (M. Zhang et al, 2021).…”

“…M. Zhang et al (2021) aimed at the problem of poor recommendation quality in the case of sparse data, and this paper proposes a recommendation algorithm for sparse data by optimizing the filling of scoring vacancies and considering the number of common scoring items. The effect of the model is more obvious with the increase of data sparsity (M. Zhang et al, 2021). showed that, with the popularization of social media, the content in social networks has increased dramatically, and recommendation systems have attracted considerable attention.…”