Development and Management of E-Commerce Information Systems Using Edge Computing and Neural Networks

Abstract

E-commerce refers to implementing e-commerce on mobile devices, cell phones, and mobile Internet connections. The fast advancement of mobile electronic gadgets and mobile Internet connections has facilitated the emergence of this new e-commerce market. The e-commerce systems contain several concealed client behavior data and forthcoming growth patterns. Data mining technologies extract valuable data and facilitate the growth of e-commerce. This article focuses on studying mobile e-commerce systems within the framework of edge computing, specifically in the setting of industrial clusters. This study examines the importance and benefits of data mining techniques in implementing e-commerce management platforms using neural networks. It also evaluates the corresponding methods of data mining and predicts purchasing trends. The study has used the benefits of grouping and back propagation neural network approaches in data analytics to categorize goods details, buying tastes, and related data. The advantage of neural networks in processing nonlinear patterns is employed to forecast forthcoming buying power. The findings demonstrate that data analytical methods and neural networks exhibit higher precision in predicting the buying pattern. The correlating factor between actual and projected usage information was 0.98, with the highest relative average inaccuracy of 2.4%. Data mining technologies effectively extract previously unrecognized relevant data and anticipated buying patterns in e-commerce platforms. Neural networks have a solid ability to predict future consumption capacity and consumption behaviors accurately.