Fuzzy Logic and Genetic Algorithm for Supply Chain Optimization in E-commerce Inventory Management

The utilisation of Information and Communication Technology (ICT) has significantly transformed industry and commerce, enabling efficient online business operations through rapid technological advancement. E-commerce platforms require effective management at both operational and systemic levels because of the numerous subsystems involved. The subsystems comprise purchasers, vendors, servers, data repositories, payment processors, and distribution networks. Supply Chain Management (SCM) is fundamentally crucial for executing tasks efficiently and ensuring customer satisfaction. This study investigates the optimisation of e-commerce supply chains through an intelligent model encompassing data preprocessing, feature selection, and model training. Prior to feature selection, data must undergo preprocessing to ensure high-quality inputs. A nonlinear methodology termed FL is utilised, which amalgamates subjective assessments from neural networks with objective results. A GA-based technique is applied to further improve these outputs using optimal weight values. A hybrid FLGA model is proposed in the study to enhance the performance of neural networks. The experimental results indicate that the proposed model effectively manages e-commerce supply chains, achieving a prediction accuracy of 97.51%. Ultimately, digital SC may be significantly enhanced by the application of intelligent methodologies such as Genetic Algorithms and Federated Learning. This offers a robust solution for optimising SC operations in the dynamic e-commerce sector.