System Dynamics in the Predictive Analytics of Container Freight Rates

Abstract

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.

An innovative tool for cost control under fragmented scenarios: The container freight index microinsurance

“…For example, actuarial methods such as the classical Burn model are often used for the pricing of weather index insurance with typical periodicity ( Han, et al, 2019 ). For the pricing of the CFIM, we adopt the derivative pricing for the following reasons: The stable matching between supply and demand of the global container shipping market and the asymmetry of shipping information leads to large and unpredictable volatilities of the container freight index ( Jeon, et al, 2021 ). Therefore, the derivative pricing based on second moments can be more suitable for quantifying the risk under the insurance scenario.…”

Analysis of influencing factors and prediction of China’s Containerized Freight Index

“…The CCFI objectively reflects the situation of the Chinese shipping market, and studying the changes in the CCFI plays a significant role in understanding the changes in the Chinese shipping industry. (Jeon et al, 2021) utilized the VECM (Vector Error Correction Model) to analyze and model the CCFI based on factors such as China's container import volume, new building prices of container ships, and second-hand prices of container ships. (Yin and Shi, 2018) collected data on freight price changes in Chinese containers to reveal the seasonal fluctuation patterns of the CCFI.…”

“…Our study contributes to both theory and practice. From a theoretical perspective, some scholars have analyzed and predicted CCFI using mixed decomposition ensemble methods based on EMD, Grey Wave, and ARMA (Chen et al, 2021) and applied system dynamics to forecast and analyze the non-complex nonlinear structure of CCFI (Jeon et al, 2021). However, there is no literature that specifically investigates the relationship between "CCBFI," "BDI," "Yangtze River Container Freight Index," "Global: Aluminum (minimum purity 99.5%, LME spot price): UK landed price," "Major Ports: Container Throughput," and "Coal Price: US Central Appalachian Coal Spot Price Index" with CCFI.…”