Forecasting container freight rates for major trade routes: a comparison of artificial neural networks and conventional models

Abstract

Major players in maritime business such as shipping lines, charterers, shippers, and others rely on container freight rate forecasts for operational decision-making. The absence of a formal forward market in container shipping necessitates reliance on forecasts, also for hedging purposes. 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 Containerized Freight Index (CCFI) as a collection of weekly freight rates published by the Shanghai Shipping Exchange (SSE) for four major trade routes. We find that, overall, VAR/VEC models outperform ARIMA and ANN in training-sample forecasts, but ARIMA outperforms VAR and ANN taking test-samples. At route level, we observe two exceptions to this. ARIMA performs better for the Far East to Mediterranean route, in the training-sample, and the VEC model does the same in the Far East to US East Coast route in the test-sample. Hence, we advise 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.