Sustainability of Shipping Logistics: A Warning Model

Abstract

The shipping industry is the foundation of the economy, and it is affected by fluctuations in the economic cycle. The mainstream of financial early warning research is quantitative modeling research. There are few systematic studies on financial early warning of shipping enterprises, and most of them still remain in the qualitative stage. This paper chooses Chinese listed shipping companies as its target, takes the economic cycle as an important reference, and then uses logistic regression, neural network, and random-forest methods to establish a model for financial warning. The random-forest model is employed to rank the importance of warning indicators. The results show that it is effective to consider macro-factors, such as the economic cycle, and the predictive accuracy of the random-forest method is higher than that of the financial warning models established by logistic regression and by the neural network. Financial alerts can help managers prepare for crises in advance. The purpose of this paper is to provide an early warning model for the sustainable development of shipping logistics.