Intelligent port data management systems to improve capability

From operations management's point of view, the nature of business models is the tool for knowing data, processing data and extracting value from data. Recently many studies advocate big data research which one common object to bring in intelligence from the huge amount of data. Nevertheless, owing to the characteristics of unstructured data, extracting the value in the big data still requires further research. This paper demonstrates a case study on container throughput forecasting model based on previous socio-economic data. The objective is to create an intelligent logistics centre for port operations. First, descriptive statistics has been conducted to describe the potential influencing factors. And then a variable selection process was applied to confirm the variables which will be included in the forecasting model. Then a forecasting model can be built by support vector machine algorithm. To evaluate the performance of the proposed method, other forecasting models were used, and the results showed that the proposed method outperform other common models, and also has the ability to help the stakeholders to make decisions.