The transition of the shipping industry towards alternative fuels is a strategic decision, largely necessitated by international environmental regulations. However, the factors influencing a shipowner’s choice of fuel at the newbuilding stage are not fully understood.
To this end, we introduce explainable artificial intelligence (XAI), which transcends traditional approaches, in an effort to reveal and explain the multitude of parameters that influence fuel decisions. Using a Light Gradient Boosting Machine (LightGBM) to analyze an extensive newbuilding dataset from Clarksons, we have identified four predictors of fuel choice: vessel size, vessel type, shipowner nationality and market cycle.
The fourth predictor, market cycle, addresses unexpected counter-cyclical investment opportunities in next-generation fuels, such as ammonia.
Our findings reconceptualize the fuel-choice dilemma as a multidimensional strategic decision framework rather than a mere technical issue. We provide shipowners with a data-driven perspective to inform their investment decisions, while offering policymakers empirical evidence with which to design more targeted regulations that account for the diverse realities of the global shipping industry.

No comments:
Post a Comment