Mining rules of decision-making for fleet composition under market uncertainty using a genetic algorithm

Abstract

This study proposes a method for determining decision-making rules on fleet composition that are effective from a perspective of profitability in the shipping industry, where there are several market uncertainties such as fuel prices, freight rates, exchange rate, transportation demand, world transportation capacity, and ship price. A simulator is used to calculate the revenue of the fleet composition based on the market scenario. Using this to optimize the buying and selling behavior of ships, decision-making rules regarding fleet composition can be determined. The rules are expressed as a vector, and a genetic algorithm (GA) is used for optimization. As a case study, the method was applied to container ships operating between Asia and Europe. The simulation revealed optimal decision-making rules. Moreover, a controlled experiment was conducted to validate the effectiveness of the rules. Participants were randomly divided into two groups: those with rules and those without rules, and they were asked to perform buying and selling behavior in a simulated environment. By comparing these groups’ profits, it is validated that the rules discovered by the method are useful because they encourage decision-making from a long-term perspective.