Answers are grounded in this paper and cite their sources.
The mass customisation logistics service model has obvious advantages in terms of improving economies of scale and meeting diverse customer needs, and the basis for applying the mass customisation model is a reasonable order batching strategy. This paper proposes a two-stage order batching and clustering strategy for massive orders gathered on cloud logistics platforms. First, based on the similarity of the logistics tasks included in an order, the Fuzzy C-Means (FCM) is used to process the first batch of orders. Subsequently, based on each batch result, a mixed-integer nonlinear programming (MINLP) order clustering model is proposed with the goal of maximising the cloud platform’s profits. Furthermore, this paper proposes an improved algorithm that combines simulated annealing and a genetic algorithm (SAGA) to optimise the FCM during the first stage and solves the order clustering model during the second stage. Through numerical experiments, it was found that the SAGA hybrid algorithm has significant advantages in terms of optimising the FCM and solving order clustering models. This work provides a new approach for cloud logistics order clustering problems, and the proposed SAGA hybrid algorithm provides a reference for solving large-scale sample clustering models.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: