System Dynamics in the Predictive Analytics of Container Freight Rates

This study proposes a two-tier cross-validation and backtesting procedure, including expanding and rolling-window test metrics in predictive analytics of container freight rates by utilizing the system dynamics approach. The study utilized system dynamics to represent the nonlinear complex structure of container freight rates for predictive analytics and performed univariate and multivariate time-series analysis as benchmarks of the conventional approach. In particular, the China containerized freight index (CCFI) has been investigated through various parametric methodologies (both conventional time-series and system dynamics approaches). This study follows a strict validation process consisting of expanding window and rolling-window test procedures for the out-of-sample forecasting accuracy of the proposed systemic model and benchmark models to ensure fair validation. In addition to the predictive features, major governing dynamics are presented in the analysis which may initiate further theoretical discussions on the economics and structure of the container shipping markets. Empirical results indicate that postsample accuracy can be affected by the sample size (training data size) in a given set of methodologies. Considering the economic challenges in the container shipping industry, the proposed methodology may help users to improve their cash-flow visibility and reduce the adverse effects of volatility in container shipping rates.