Unstructured big data analytics for retrieving e-commerce logistics knowledge

Abstract

The divergent evolution of e-commerce has complicated its correspondingly logistics management. However, few studies have explored e-commerce logistics business models via big data analytics. Hence, this investigation explores e-commerce logistics business models from unstructured big data. Specifically, this work develops a hybrid content analytical model to scrutinize essential knowledge of e-commerce logistics. The empirical results of the proposed model incorporate theories of resource dependence theory (RDT) and innovation diffusion theory (IDT) to generate logistical strategies. Ten critical themes of e-commerce logistics from topic mining are “Southeast Asia’s e-commerce logistics payments”, “E-commerce order management”, “E-commerce logistics cloud services”, “E-commerce logistics package management”, “Europe e-commerce trends”, “India’s e-commerce logistics”, “E-commerce distribution management”, “Tax policies”, “E-commerce logistics platforms”, and “E-commerce logistics networks”. Moreover, the fundamental rule of “cross-border e-commerce logistics” is uncovered by the association rules model. The proposed hybrid content analytics framework provides a research foundation for e-commerce logistics management. Furthermore, e-commerce logistics can be implemented by vital strategies: “Establish inter-organizational and technical collaboration to create positive operations performance” and “Comprehend law, policy, and cultural differences to customize appropriate technologies of e-commerce logistics”.