A hybrid NSGA-II algorithm for the closed-loop supply chain network design in e-commerce

Abstract

Designing the supply chain network is one of the significant areas in e-commerce business management. This concept plays a crucial role in e-commerce systems. For example, location-inventory-pricing-routing of an e-commerce supply chain is considered a crucial issue in this field. This field established many severe challenges in the modern world, like maintaining the supply chain for returned items, preserving customers' trust and satisfaction, and developing an applicable supply chain with cost considerations. The research proposes a multi-objective mixed integer nonlinear programming model to design a closed-loop supply chain network based on the e-commerce context. The proposed model incorporates two objectives that optimize the business's total profits and the customers' satisfaction. Then, numerous numerical examples are generated and solved using the epsilon constraint method in GAMS optimization software. The validation of the given model has been tested for the large problems via a hybrid two-level non-dominated sort genetic algorithm. Finally, some sensitivity analysis has been performed to provide some managerial insights.

Research on the Application of Multi-Objective Algorithm Based on Tag Eigenvalues in e-Commerce Supply Chain Forecasting

“…This indicates that the SI-LSF algorithm has the highest predictive performance in supply chain demand and has strong applicability. This result is basically consistent with the results of Moghadam et al [27]. Overall, the SI-LSF algorithm can achieve good prediction in supply chain demand after data preprocessing and feature selection, and has strong practicality.…”

A Novel Scenario-Based Bi-objective Optimization Model for Sustainable Food Supply Chain During the COVID-19: a Case Study

“…Besides, finding the best weights is a time-consuming action that makes it harder to use goal programming. In addition, it is one of the posterior methods utilized to a multi-objective integer programming problem and can generate the exact Pareto set provided that the step size is appropriately chosen (Moghadam et al 2021 ). Therefore, the augmented epsilon-constraint method has been implemented (Mavrotas and Florios 2013 ).…”

A location-inventory-pricing model for a three-level supply chain distribution network

“…Rabbani et al [25] incorporated pricing decisions into the traditional location-inventory problem in municipal solid waste management. Moghadam et al [23] studied location-inventory-pricing problem along with routing for a four-level closed-loop supply chain in the e-commerce context. They focused on hybrid heuristic approach for solving this problem.…”