A Novel Neurodynamic Model for Data Envelopment Analysis: A Case Study on Iran’s Olympic Sports Caravan

The article introduces a novel neurodynamic model leveraging Recurrent Neural Networks (RNNs) to solve Data Envelopment Analysis (DEA) problems. DEA is a technique used to evaluate the relative efficiency of decision-making units with multiple inputs and outputs. Traditional DEA methods can be computationally intensive, especially with large datasets. The proposed RNN model reformulates the DEA problem into a dynamic system, allowing for faster and more efficient solutions. The model is validated through a case study on Iran’s Olympic Sports Caravan, demonstrating its practical applicability and superior performance compared to existing methods. The article also includes theoretical analysis, proving the convergence and stability of the proposed model, making it a significant contribution to the field of optimization and neural network applications.