In a bid to streamline global supply chains and cut down on costly delays, a Nigerian researcher has developed a machine learning model that predicts inland container delivery times with moderate accuracy. Godwin Nwachukwu Nkem, an operations specialist at Lekki Freeport Terminal in Lagos, leveraged historical data to create a tool that could help shipping lines, freight forwarders, and port authorities plan more efficiently.
The model, detailed in a recent study published in the Journal of Maritime Transportation Technology Science (Jurnal Sains Teknologi Transportasi Maritim), uses a Random Forest Regressor to forecast delivery times based on factors like container size, type, shipping line, dispatch day, and temporal patterns. “Accurate prediction of inland container delivery times is crucial for enhancing operational efficiency, minimizing demurrage and detention costs, and improving customer satisfaction across global supply chains,” Nkem explained.
For maritime professionals, this means better planning and reduced uncertainty. The model’s performance metrics—a Mean Absolute Error of 4.59 days and a Root Mean Squared Error of 10.55 days—show it’s not perfect, but it’s a step in the right direction. “The findings have practical implications for shipping lines, freight forwarders, port authorities, and inland terminal operators seeking to optimize logistics planning,” Nkem added.
The commercial impacts are significant. By predicting delivery times more accurately, companies can reduce demurrage and detention costs—fees incurred when containers are held longer than agreed. This is particularly relevant for ports and terminals, where efficient turnaround times are critical. The model also offers opportunities for inland terminal operators to better manage resources and improve service levels.
While the study highlights the potential of machine learning in maritime logistics, it also acknowledges areas for improvement. Visualizations like learning curves and feature importance plots suggest that refining the model could enhance its predictive power. “Supporting visualizations… illustrate the model’s strengths and areas for further refinement,” the study notes.
For the maritime sector, this research opens doors to smarter logistics planning. As supply chains become more complex, tools like Nkem’s model could be a game-changer, helping companies stay ahead of the curve. The study contributes to the growing field of intelligent logistics and maritime informatics, offering a data-driven approach to improving inland delivery predictability.