Deep learning-based container throughput forecasting: a triple bottom line approach

Abstract

Purpose

Container throughput forecasting plays a pivotal role in strategic, tactical and operational level decision-making. The determination and analysis of the influencing factors of container throughput are observed to enhance the predicting accuracy. Therefore, for effective port planning and management, this study employs a deep learning-based method to forecast the container throughput while considering the influence of economic, environmental and social factors on throughput forecasting.

Design/methodology/approach

A novel multivariate container throughput forecasting method is proposed using long short-term memory network (LSTM). The external factors influencing container throughput, delineated using triple bottom line, are considered as an input to the forecasting method. The principal component analysis (PCA) is employed to reduce the redundancy of the input variables. The container throughput data of the Port of Los Angeles (PLA) is considered for empirical analysis. The forecasting accuracy of the proposed method is measured via an error matrix. The accuracy of the results is further substantiated by the Diebold-Mariano statistical test.

Findings

The result of the proposed method is benchmarked with vector autoregression (VAR), autoregressive integrated moving average (ARIMAX) and LSTM. It is observed that the proposed method outperforms other counterpart methods. Though PCA was not an integral part of the forecasting process, it facilitated the prediction by means of “less data, more accuracy.”

Originality/value

A novel deep learning-based forecasting method is proposed to predict container throughput using a hybridized autoregressive integrated moving average with external factors model and long short-term memory network (ARIMAX-LSTM).

Citation

Shankar, S., Punia, S. and Ilavarasan, P.V. (2021), "Deep learning-based container throughput forecasting: a triple bottom line approach", Industrial Management & Data Systems, Vol. 121 No. 10, pp. 2100-2117. https://doi.org/10.1108/IMDS-12-2020-0704