Munim, Ziaul Haque, Schramm, Hans-Joachim. 2021. Forecasting container freight rates for the major trade routes: a comparison of artificial neural network and conventional models. Maritime Economics and Logistics. 23 (2), 310-327.

RIS

@ARTICLE{Munim2021,
title = {Forecasting container freight rates for the major trade routes: a comparison of artificial neural network and conventional models},
author = {Ziaul Haque Munim and Hans-Joachim Schramm},
year = {2021},
doi = {https://doi.org/10.1057/s41278-020-00156-5},
url = {https://link.springer.com/journal/41278},
volume = {23},
number = {2},
language = {EN},
pages = {310-327},
journal = {Maritime Economics and Logistics},
abstract = {Major players in the maritime business such as shipping lines, charterers, shippers, and others rely heavily on container freight rate forecasts for operational decision making. The non-existence of a formal forward market in the container industry makes it necessary for them to rely on forecasts for their hedging strategy purposes, too. Thus, to identify better performing forecasting approaches, we compare three models, namely, Autoregressive Integrated Moving Average (ARIMA), Vector Autoregressive (VAR) or Vector Error Correction (VEC) and Artificial Neural Network (ANN) models. We examine the China containerised Freight Index (CCFI) as a collection of weekly freight rates published by the Shanghai Shipping Exchange (SSE) in four major trade routes. Overall, VAR/VEC models outperform ARIMA and ANN in training-sample forecasts, but ARIMA outperforms VAR and ANN taking test-samples. On route level, we observe two exceptions to this. ARIMA performs better for the Far East to Mediterranean in the training-sample, and the VEC model did the same in the Far East to US East Coast route in the test-sample. Hence, we advise the industry players to use ARIMA for forecasting container freight rates for major trade routes ex-China except for VEC in the case of the Far East to US East Coast route},
}