Capesize Voyage Speed Optimization: A Reinforcement Learning Model for Fuel, Earnings, and CII

Every Capesize voyage speed decision is a trade-off between fuel cost, earnings, and carbon compliance. The call is made voyage by voyage, while bunker prices, freight rates, and CII ratings keep moving.

Conducted in collaboration with Bayes Business School, this analysis draws on more than 130,000 voyages from VesselsValue’s Trade AIS tracking to test whether a reinforcement learning model could make that call better than the market does.

Read the full analysis to see where the model’s speed compared to the speed operators actually sailed, and where they diverged across fuel, earnings, and CII.