فهرست نشریات علمی دسترسی آزاد ایران

Financial dissatisfaction is a critical factor influencing corporate success or failure. This study introduces two artificial intelligence (AI)-based models to predict factors contributing to financial dissatisfaction among managers of financially distressed firms. In the first phase, relevant data were gathered through a literature review. In the second phase, additional data were collected via questionnaires and interviews (Delphi method) with senior managers to ensure theoretical saturation. The Altman Z-score was then used to identify financially distressed companies. The study’s statistical population included 166 senior managers from 50 financially distressed firms listed on the Tehran Stock Exchange. Data were collected through a structured questionnaire covering seven dimensions and 54 indicators. Two AI models—Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS)—were applied to analyze the predictive power of financial dissatisfaction factors. The first model employed a multilayer perceptron (MLP) neural network with a hyperbolic tangent activation function, while the second used an ANFIS framework with a five-layer Sugeno-type neural network containing 143 neurons in the hidden layer and trained using the Levenberg-Marquardt algorithm. Comparative analysis revealed that both models effectively identified key financial dissatisfaction factors, but the ANN model outperformed ANFIS, achieving a mean correlation coefficient (R²) of 0.98 (training) and 0.96 (validation), with a lower mean squared error (MSE) of 0.002120 and 0.003953, respectively. These findings highlight ANN’s superior predictive accuracy, making it a valuable tool for assessing financial distress among executives.