Abstract: A monitoring system is required for the offshore fishing capacity. Mathematical modelling can also be applied to analyze the impact of fishing vessel parameters on fishing capacity, from the perspectives of fishery engineering and ship design. However, it is still lacking in the fishing capacity of a single vessel. Only a few influencing factors have been considered, leading to the insufficient analysis of the subjective and objective weights of each influencing factor. Consequently, there is a high demand for the quantitative fishing capacity of a fishing vessel. In this study, an assessment model of single-vessel fishing capacity was proposed to consider the multiple influencing factors. The fishing data was also collected to conduct modelling analysis. Firstly, a comprehensive analysis was made to determine the impact of each fishing vessel parameter on fishing capacity. An evaluation index system of single-vessel fishing capacity was then established to combine the opinions of experts and fishermen in the fields. The indicators were divided into the quantifiable and non-quantifiable ones. Preliminary evaluation criteria were also formulated for the non-quantifiable indicators. Secondly, a questionnaire titled "Questionnaire on the Weight of Factors Affecting the Fishing Capacity of China's Offshore Fishing Vessels" was distributed to collect the scoring data from experts and fishermen. The analytic hierarchy was used to calculate the weights of each indicator. The results indicated that the weights of each indicator were as follows: fishing equipment (0.108), power (0.094), trawl (0.074), operating time (0.071), total tonnage (0.049), fish detection equipment (0.047), gillnet (0.040), captain (0.032), net (0.028), purse seine (0.024), fishing (0.021), operating environment (0.019), steel material (0.019), cover net (0.017), fiberglass material (0.016), ship age (0.013), wooden material (0.012). The weights of fishing gear-related indicators were: main size of net gear (0.402), net structure (0.149), assembly technology (0.093), and manufacturing materials (0.051). Finally, the advantages of subjective and objective weights were given to combine the subjective weights from the analytic hierarchy process (AHP) and the objective weights from the Random Forest using the additive synthesis, and game theory. The minimum discriminant information was obtained from the target weights, in order to facilitate further analysis and calculations in the following sections. A validation analysis was then conducted. Given that the fishing vessel capacity assessment model was suitable for the motorized fishing vessels, a random sample of data from 12 motorized fishing vessels was collected for validation. Spearman rank correlation coefficient was used to calculate the graded correlation coefficient between the fishing capacity evaluation and the actual catch. The results revealed that the outcomes with the game theory shared the highest correlation, with a correlation coefficient as high as 0.937. Therefore, the combined weights were used as the target for the evaluation indicators. The finding can greatly contribute to the scientific management of offshore fisheries, in order to alleviate the overfishing in the sustainable marine industry.