Data analytics and throughput forecasting in port management systems against disruptions: a case study of Busan Port

Forecasting cargo throughput is an essential albeit challenging task in ensuring efficient seaport management. In this study, data analytics is employed to analyze the nonlinear dynamic behaviors, as well as disruptions in port throughputs. Further, nonlinear analytical methods, including the Lyapunov exponent (LE), information entropy, Hurst exponent, and wavelet decomposition, are employed to explore the complex dynamic behavior of port throughput under supply chain disruptions. By employing the discrete wavelet transform (DWT) and the long short-term memory (LSTM) network, we develop a novel hybrid model of port throughput forecasting. DWT is employed to decompose the original data into a finite set of frequency components, so that the various hidden features of cargo throughput can be extracted via different modes, such as the trend, residual, and seasonal components. Thereafter, each component, obtained from the DWT spectra, is predicted via a machine learning model. Additionally, hypothesis testing, model evaluation, and statistical significance tests are employed to comprehensively evaluate the introduced forecasting models. Regarding prediction accuracy and efficiency, our extensive simulation results confirm the superiority of the hybrid strategy over five benchmarked models. Finally, by employing business forecasting software, we show that the robust hybrid strategy achieves accurate predictions of port throughputs against market disruptions. Our findings can help decision-makers understand disruption mechanisms in port systems, thus enabling them to successfully achieve their business goals.