AI based fuzzy MCDM models: Comparison and evaluation of dissimilar outcomes, an application to enhance pilot recruitment process

Pilot recruitment is critical as they pose a multifaceted challenge for civilian and military organizations due to the complex traits impacting their missions and performance. In this study, a novel set of criteria and sub‐criteria were determined to compare twelve candidate pilots. Numerically immeasurable, imprecise, and non‐linear continuous fuzzy linguistic traits (variables) were studied which make the work unique and challenging due to individual preferences and disagreements between decision‐makers (DMs). The outcomes of three distinct fuzzy multiple criteria decision‐making (MCDM) approaches; fuzzy TOPSIS, fuzzy VIKOR, and fuzzy PROMETHEE were evaluated with trapezoidal fuzzy numbers (TFNs) to sort the positions of candidate pilots. Moreover, a unique defuzzification ranking method was employed to adjust the results of fuzzy MCDM methods for the synthesis and evaluation of outcomes of the pilot selection problem. All these efforts make the paper original and outstanding. Our findings and analysis suggested that fuzzy TOPSIS and PROMETHEE methods' outcomes showed maximum close similarity for ranking positions. However, substantial distinctions were noted when comparing these outcomes with the fuzzy VIKOR approach. Yet, the mission of predicting and revealing the best candidates is related to several traits, their weights, and the methods selected. Therefore, since vague information and ambiguous preferences match fuzzy superiority, a comprehensive and unbiased evaluation was achieved, ensuring the integrity of the decision‐making process. The results can be employed to enhance the safety and efficiency of airline operations and ensure that the most qualified and competent pilots are selected for the job.