Multi-criteria methods are used in systems designed to support decision-making or for prediction. One of these methods is the Characteristic Objects Method (COMET), which uses expert knowledge to calculate preference values when creating a rule base. The number of Characteristic Objects (COs) pairs necessary to perform comparisons depends on the model’s structure, the number of criteria and characteristic values.
In this paper, it was decided to build a complex MCDM model based on the COMET method, which was used to predict the chances of overtaking during pit stops in Formula 1 races. To improve the performance of the model and reduce the necessary pairwise comparisons of COs, it was decided to split the structure into submodels aggregating criteria with similar characteristics to reduce the complexity of the problem. Additionally, the influence of each criterion on the obtained preference values and the final result was examined. By restructuring the model, it was possible to reduce the number of comparisons while maintaining the designed model’s correct operation.
Data udostępnienia | 29 lis 2022, 12:10:07 |
---|---|
Data mod. | 29 lis 2022, 12:10:07 |
Dostęp | Publiczny |
Aktywnych wyświetleń | 0 |