Research On Forecast And Influencing Factors Of New Ship Signing

The international shipping industry is an important commercial trade link connecting various countries and regions in the world.The thriving development of the international shipping industry directly drives the development of the shipbuilding industry.The shipbuilding industry is an important part of the national economy.It not only provides equipment for the development of marine resources,but also provides a necessary platform for world trade.At present,Asia is the center of the world's shipbuilding industry.China,South Korea,and Japan account for more than 90% of the world's shipbuilding,which plays an important role in the development of the world's shipbuilding industry.More than 80% of the world's international trade transportation was completed by shipping.The trend of ship market demand has become a matter of great concern to shipyards and shipowners.At present,some scholars have done some research on the prediction of ship orders.But most of them forecast ship orders by using ship orders itself,lack of the quantitative analysis of the external influence factors.Most studies on the shipbuilding industry competitiveness of China,South Korea and Japan's three shipbuilding powers are from a macro perspective to analyze the development status of the shipbuilding industry.Few scholars have analyzed the ship competition in the three countries from a quantitative perspective.This paper mainly studies the causality between the influencing factors of the new ship orders and the new orders,and analyzes the competition relationship between the three major shipbuilding countries in China,South Korea and Japan on the new ship orders.Finally,this paper makes a prediction research on the new signing orders of the ship.The main research focus of this article includes:(1)Analyze the influencing factors of ship orders,and conduct a strict causality test on the relationship between the newly signed ship orders and important influencing factors.The causal relationship between dry bulk carrier orders and the Baltic dry bulk freight index(BDI)and second-hand ship trading volume is first studied using the marginal cointegration test based on the autoregressive distribution hysteresis model,and then tested by the Granger causality theory.We find that there is a long-term equilibrium relationship between the new bulk cargo ships and BDI and second-hand ship trading volume.There is a one-way Granger causality between the new carrier orders and the BDI index,and the BDI index is the Granger cause of the new carrier order.(2)Referring to relevant theoretical knowledge of population ecology,the Lotka-Volterra model is introduced into the system of new ship signing orders,and the Lotka-Volterra competition model for newly signing ship orders about China,South Korea and Japan is established.In addition,the parameter estimation method of the integral model proposed by Kloppers and Greeff and the nonlinear least squares method are used to estimate the parameters of the newly signed Lotka-Volterra model for shipbuilding in China,South Korea and Japan,and this paper analyzes the competition and cooperation between China,South Korea and Japan.The results of the study find that China and South Korea are in a competitive relationship with new signings of ship orders,China and Japan are in a reciprocal relationship with new signings of ship orders,and South Korea and Japan are in a competitive relationship with new signings of ship orders.(3)This paper adopts the classic time series forecasting model ARIMA model,the VECM model with the explanatory variable BDI index,the new Lotka-Volterra competition model for ships in China,Japan and Korea,and the Lotka-Volterra competition model optimized after adding the explanatory variable BDI index to China,South Korea and Japan ship new signing ship orders to make predictions.The five evaluation indexes MAE,SMAPE,NMSE,MAPE,and RMSE are used to compare the prediction accuracy of the four models.The research results show that compared with the ARIMA model,the prediction effect of the VECM model and the Lotka-Volterra model is better.