Resilience Appraisal for Iranol Oil Company: Application of Adaptive Neuro-Fuzzy Inference System

In recent years, resilience has attracted much attention for understanding how organizations can prepare and respond to the turbulence environment. Despite the growing body of empirical research, previous studies emphasized on need for greater clarity in measuring organizational resilience. This study presents a systematic framework for measuring organizational resilience in Iranol Oil Company, a leading lubricant and petroleum product manufacturer in Iran, during 2024. Leveraging qualitative methods, this research identified key resilience indicators across five dimensions: organizational adaptability, collaborative factors, change management, HR management, and production management. A structured methodology was employed, encompassing a two-round fuzzy Delphi method to refine indicators and their categorization into five groups. Data collection involved 126 qualified employees, with a training-testing-validation split to ensure model accuracy and generalizability. The ANFIS model, with Gaussian membership functions, integrated linguistic and numerical inputs to generate resilience predictions through a multi-layered architecture. Results demonstrated high alignment between predicted and actual values, with mean square errors of 0.00244, 0.00279, and 0.00113 for training, testing, and validation datasets, respectively. A sensitivity analysis confirmed the robustness of the model under extreme conditions. The findings indicate that Iranol demonstrates moderate to high resilience levels, with opportunities to enhance adaptability, innovation, and employee engagement.