Demand Forecasting of E-Commerce Enterprises Based on Horizontal Federated Learning from the Perspective of Sustainable Development

Abstract

Public health emergencies have brought great challenges to the stability of the e-commerce supply chain. Demand forecasting is a key driver for the sound development of e-commerce enterprises. To prevent the potential privacy leakage of e-commerce enterprises in the process of demand forecasting using multi-party data, and to improve the accuracy of demand forecasting models, we propose an e-commerce enterprise demand forecasting method based on Horizontal Federated Learning and ConvLSTM, from the perspective of sustainable development. First, in view of the shortcomings of traditional RNN and LSTM demand forecasting models, which cannot handle multi-dimensional time-series problems, we propose a demand forecasting model based on ConvLSTM. Secondly, to address the problem that data cannot be directly shared and exchanged between e-commerce enterprises of the same type, the goal of demand information sharing modeling is realized indirectly through Horizontal Federated Learning. Experimental results on a large number of real data sets show that, compared with benchmark experiments, our proposed method can improve the accuracy of e-commerce enterprise demand forecasting models while avoiding privacy data leakage, and the bullwhip effect value is closer to 1. Therefore, we effectively alleviate the bullwhip effect of the entire supply chain system in demand forecasting, and promote the sustainable development of e-commerce companies.

Research on the Purchase Intention of Children's Educational Products Based on Feedforward Neural Network and Factor Analysis

“…People are more likely to accept the more familiar objects, which enables the word of mouth information communicators with high relationship strength to put forward more suggestions for the receiving decision. Therefore, product word of mouth is one of the important factors affecting consumers' purchase intention [9].…”

Research on Sustainable Management Strategies for the Machine Tool Industry during the COVID-19 Pandemic in Taiwan

“…"Sustainability" is an economic development that can meet the needs of this generation without compromising the ability of future generations to meet their needs. As far as enterprises are concerned, this includes issues such as corporate social responsibility, corporate citizenship, improving corporate management of social and environmental affects, and improving the participation of stakeholders, an important role in the processes of social innovation and sustainable development [19]. In recent years, sustainable operation has been paid more attention in order to achieve the goal of sustainable operation of the enterprise.…”

Power grid investment forecasting method based on PSO‐GRU neural network

“…These factors can be divided into short‐term influencing factors, medium‐term influencing factors, and long‐term influencing factors. The short‐term, medium‐term, and long‐term influencing factors all work together to make the power grid investment have complex nonlinear, and nonstationary characteristics 18,19 . Therefore, accurate and effective prediction of power grid investment has become the key and difficult problem faced by power grid enterprises and power planning departments.…”

“…The short-term, medium-term, and long-term influencing factors all work together to make the power grid investment have complex nonlinear, and nonstationary characteristics. 18,19 Therefore, accurate and effective prediction of power grid investment has become the key and difficult problem faced by power grid enterprises and power planning departments. A reasonable forecasting method is an important prerequisite to improve the effectiveness and accuracy of future power grid investment forecasting.…”