The data-driven analytics for investigating cargo loss in logistics systems

Abstract

Purpose - Cargo loss has been a major issue in logistics management. However, few studies have tackled the issue of cargo loss severity via business analytics. Hence, the purpose of this paper is to provide guidance about how to retrieve valuable information from logistics data and to develop cargo loss mitigation strategies for logistics risk management. Design/methodology/approach - This study proposes a research design of business analytics to scrutinize the causes of cargo loss severity. Findings - The empirical results of the decision tree analytics reveal that transit types, product categories, and shipping destinations are key factors behind cargo loss severity. Furthermore, strategies for cargo loss prevention were developed. Research limitations/implications - The proposed framework of cargo loss analytics provides a research foundation for logistics risk management. Practical implications - Companies with logistics data can utilize the proposed business analytics to identify cargo loss factors, while companies without logistics data can employ the proposed cargo loss mitigation strategies in their logistics systems. Originality/value - This pioneer empirical study scrutinizes the critical cargo loss issues of cargo damage, cargo theft, and cargo liability insurance through exploiting real cargo loss data.