An Optimal Model based on Multifactors for Container Throughput Forecasting

Abstract

Containerization plays an important role in international trade. Container throughput is a key indicator to measure the development level of a port. In this paper, Lianyungang Port and Shanghai Port are chosen to study the method for container throughput forecasting. Gray model, triple exponential smoothing model, multiple linear regression model, and backpropagation neural network model are established. Five factors are selected as influential factors. They are total retail sales of consumer goods, gross domestic product of the local city, import and export trade volume, total output value of the second industry and total fixed assets investment. The growth and the raw datasets are used in the prediction, respectively. The datasets from 1990 to 2011 are chosen to build models and the ones from 2012 to 2017 are used to assess the performance of the models. By comparison, the backpropagation neural network model is applicable to both Shanghai Port and Lianyungang Port for container throughput forecasting. The volume of container throughput at both ports from 2018 to 2020 is predicted.