Multi-objective hub-spoke network design of perishable tourism products using combination machine learning and meta-heuristic algorithms

In this research, the objective is to design a multi-objective Hub-Spoke network of perishable tourism products. In order to consider the perishable factor of the products, some collection centers are considered for the products which are perished. Accordingly, the combination of Hub-Spoke network and supply chain is assessed here. Moreover, this combination is to use transportation discounts in the supply chain network. The desired combination is done in such a way that the distributors are considered as a set of hubs. As the first objective is to reduce network costs and the second objective is to reduce the emission of environmental pollutants, for the model-based solution method, a combined solution method of meta-heuristic algorithm with machine learning technique has been developed, called Multi-Objective Artificial Immune System algorithm with Machine Learning (ML-MOAIS). Also, MOAIS and NSGA-II algorithms have been used to evaluate this solution method. Employing machine learning (ML) approach leads to limiting the space for problem solving and the faster convergence of the solutions to a feasible solution. This is time-saving and cost-effective. Evaluations and comparisons have been performed in two groups of qualitative and quantitative indicators and the results show that the designed algorithm has been superior to the MOAIS and NSGA-II algorithms on average in both qualitative and quantitative indicators. A detailed analysis of the indicators shows that the Pareto solutions of the proposed algorithm have a higher number, more spread around the Pareto front, and also a higher quality in terms of cost and emission of environmental pollutants.