Preference Evaluation and Recommendation of Athletes for National Traditional Sports Training Using an Intelligent Method Based on Picture Fuzzy Knowledge

In sports, athletes’ initial training is crucial for their whole career. Initial training at the relevant board athletes are professionally trained for national and international competitions. However, the selection of potential athletes for traditional training is very hectic and uncertain due to the involvement of various factors. Thus, we need an intelligent approach to efficiently deal with the uncertain factors in selecting and recommending athletes for training camp. A multi-attribute group decision-making (MAGDM) approach offers a structured framework for evaluating and selecting athletes, considering various attributes that reflect stakeholder preferences and needs. In MAGDM, the human point of view is crucial. Several frameworks deal with the extraction of information in the decision-making process. The interval-valued picture fuzzy rough set (IVPFRS) contributes significantly to lower the uncertainty in the data derived from real-world scenarios. In this study, new aggregation operators (AOs) based on the Schweizer-Sklar t-norm (SSTN) and the Schweizer-Sklar t-conorm (SSTC), i.e., interval-valued picture fuzzy rough weighted averaging (IVPFRSSWA) and interval-valued picture fuzzy rough weighted geometric (IVPFRSSWG), are developed to aggregate the data in the form of the interval-valued picture fuzzy rough values (IVPFRVs). After their fundamental qualities are examined, the created AOs are used to solve the MAGDM problem. The results vary based on the values of the involved parameters in SSTN and SSTC. The findings obtained also contrast with those of other known AOs. Additionally, a graphic representation of each observation and result is provided.