Purpose Better forecasting always leads to better management and planning of the operations. The container throughput data are complex and often have multiple seasonality. This makes it difficult to forecast accurately. The purpose of this paper is to forecast container throughput using deep learning methods and benchmark its performance over other traditional time-series methods. Design/methodology/approach In this study, long short-term memory (LSTM) networks are implemented to forecast container throughput. The container throughput data of the Port of Singapore are used for empirical analysis. The forecasting performance of the LSTM model is compared with seven different time-series forecasting methods, namely, autoregressive integrated moving average (ARIMA), simple exponential smoothing, Holt–Winter’s, error-trend-seasonality, trigonometric regressors (TBATS), neural network (NN) and ARIMA + NN. The relative error matrix is used to analyze the performance of the different models with respect to bias, accuracy and uncertainty. Findings The results showed that LSTM outperformed all other benchmark methods. From a statistical perspective, the Diebold–Mariano test is also conducted to further substantiate better forecasting performance of LSTM over other counterpart methods. Originality/value The proposed study is a contribution to the literature on the container throughput forecasting and adds value to the supply chain theory of forecasting. Second, this study explained the architecture of the deep-learning-based LSTM method and discussed in detail the steps to implement it.

No abstract

PurposeThe literature on Maritime Transportation (MT) is experiencing a transition phase where the focus of the research is repositioning. It registered steep growth in recent years with its beginning articles on the concepts of cost minimization to the current focus on achieving sustainable operational effectiveness using Information and Communication Technologies (ICTs). Thus, this becomes a right time to investigate the trajectory of research on MT.Design/methodology/approachThe proposed study aims to explore the potential of data analytics techniques such as data mining and network analytics to reflect the trajectory of research in the maritime supply chain over time. This study identifies the eight main dimensions of the research published under maritime paradigm through network analytics. The in-depth review of these dimensions rendered us to segregate them further into sub-dimensions for the ease of understanding and interpretability. Further, the text mining is employed to extract thematic evolution of the research.FindingsThe evolved themes are completely exclusive from the conventional MT research with artificial intelligence, digital storage, waste management and biofuels emerging as contemporary themes. It is found that although there are a sufficient amount of literature on sustainable port practices but their policy implications are still underexplored. The inter-dimension research is needed to achieve the motive of economic efficiency and environmental sustainability simultaneously.Originality/valueThe study has contributed on the methodology side of conducting literature reviews. The dimensions, sub-dimensions and themes are obtained using data analytics tools and techniques. This omits the possibility of personal bias and thus making the results verifiable.

No abstract

No abstract