top of page
Image by SJ Objio
Title: Predicting Vessel Chartering Cost and Time-Charter Rate Movement
Organization

Vale - IBM - Deloitte

Period

January 2018 - December 2019

Status

Completed

Est. Budget

USD 2.4M

Est. Business Benefit

USD 18.0M

Indicative Value-to-cost

7.5x

Keywords

TC rate forecasting, Azure Synapse, Power BI, vessel chartering, freight optimisation, shipping intelligence

Benefit basis

Estimated value from improved chartering timing, lower TC-rate exposure, reduced manual analysis effort, and better integration of vessel supply-demand signals.

Business Challenges 
Time-charter (TC) rates for bulk material shipping are dynamic and strongly influence delivered product cost. Chartering decisions depend on short-term supply, expected demand, vessel position, competitor activity, port congestion, cargo requirements, and market volatility. The business needed an integrated architecture and predictive capability to forecast TC-rate movement over the next 30 to 60 days and provide more informed chartering recommendations.
Expanded Technical Solution
The project delivered an integrated cargo-demand and global-vessel-movement analytics platform. Data was consolidated into a scalable analytical warehouse, with Azure Synapse and Power BI forming the core data and visualisation layer. Forecasting models estimated TC-rate movement using vessel supply-demand indicators, shipment schedules, historical rates, voyage patterns, port congestion, vessel class, and external market signals. The application generated intelligent suggestions that helped users compare timing, route, vessel class, and chartering options.
Technical Work Packages/Methods
  • Integrated cargo demand, vessel availability, vessel movement, historical TC rates, port congestion, route distance, fixture history, and external market variables.
  • Built a reusable data architecture for supply-demand projects and freight-rate forecasting.
  • Implemented forecasting methods including time-series models, machine-learning regression, and scenario-based sensitivity analysis.
  • Developed Power BI views for TC-rate forecast, confidence range, regional supply-demand balance, route analysis, and recommended action windows.
  • Created model-monitoring processes for forecast accuracy, forecast drift, and market-condition changes.
Key Deliverables
  • Integrated shipping analytics architecture in Azure Synapse.
  • TC-rate forecasting model and scenario engine.
  • Power BI commercial decision dashboard.
  • Reusable data foundation for vessel supply, demand, destination, and chartering projects.
Results and Value Created
The project increased the ability of commercial teams to anticipate freight-rate movement, evaluate chartering timing, and make better decisions under uncertain vessel market conditions. It also created a reusable architecture for related shipping intelligence products. The estimated benefit reflects lower chartering cost, reduced decision latency, improved freight-market timing, and better use of available vessels.
bottom of page