State-space TBATS model for container freight rate forecasting with improved accuracy

Abstract

This study forecasts container freight rates using three seasonal univariate models — Seasonal Autoregressive Integrated Moving Average (SARIMA), Seasonal Neural Network Autoregression (SNNAR) and the state-space TBATS model. As a proxy for weekly container freight, China Container Freight Index (CCFI) is forecasted, collected from the Shanghai Shipping Exchange (SSE) from January 2010 to December 2018, in total 470 data points. For cross-validation, two expanding training-samples, one from January 2010 till December 2016 and another from January 2010 till December 2017 are analysed. Subsequently, two test-samples, January-December 2017 and January-December 2018 are forecasted. We find that the TBATS model or a combination of TBATS and SARIMA forecasts outperform SARIMA and SNNAR as well as their combinations both in training and test-sample forecast. Moreover, for robustness of the cross-validation, each test-sample data point has been forecasted using model re-estimation, which improves forecast performance of SARIMA and SNNAR models, but not of TBATS.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 37 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.