A new-type deep learning model based on Shapley regulation for containerized freight index prediction

Authors

Yen-Chang Shih, Department of Shipping and Transportation Management, National Taiwan Ocean University, Keelung 202301, Taiwan
Ming-Shue Lin, Department of Electrical Engineering, National Taiwan Ocean University, Keelung 202301, Taiwan
Taih-Cherng Lirn, Department of Shipping and Transportation Management, National Taiwan Ocean University, Keelung 202301, Taiwan
Jih-Gau Juang, Department of Communications, Navigation and Control Engineering, National Taiwan Ocean University, Keelung 202301, TAIWANFollow

Abstract

In this study, we have crafted an innovative methodology that represents a groundbreaking synthesis of deep learning techniques with cooperative game theory. In this study, we use the accuracy of data prediction by different LSTM models as a measurement index and assign different LSTM models corresponding weights through the Shapley value calculation method to construct a more accurate predictive analysis model. We use this improved Shapley regulation model to calibrate a long short-term memory (LSTM) neural network by using historical freight data to predict the China Container Freight Index (CCFI), the leading export container freight index commonly used in China. Afterward, it is found that the neural networks calibrated in this way reduce their prediction bias in terms of mean absolute percentage error (MAPE), mean absolute error (MAE), root mean square error (RMSE), and mean square error (MSE) to improve prediction accuracy.

Recommended Citation

Shih, Yen-Chang; Lin, Ming-Shue; Lirn, Taih-Cherng; and Juang, Jih-Gau (2024) "A new-type deep learning model based on Shapley regulation for containerized freight index prediction," Journal of Marine Science and Technology: Vol. 32: Iss. 1, Article 3.
DOI: 10.51400/2709-6998.2729
Available at: https://jmstt.ntou.edu.tw/journal/vol32/iss1/3