Performance Evaluation of Enterprise Collaboration Based on an Improved Elman Neural Network and AHP-EW

In order to mitigate the influence of human subjectivity on indicator weights in the performance evaluation of enterprise collaboration, and explore the nonlinear relationship between the enterprise collaboration influencing factors and the evaluation results, this paper propose a combined performance evaluation model based on AHP-EW and an improved Elman neural network. Firstly, based on the characteristics of collaboration among manufacturing enterprises, the evaluation system for the collaborative performance of manufacturing enterprises is constructed from three dimensions. Moreover, this study combines subjective and objective weighting methods to obtain comprehensive weights that take into account both expert experience and objective information. Then, an improved Elman neural network is proposed and trained to predict and evaluate the collaborative performance indicator data, which greatly shortens the evaluation time and improves evaluation accuracy. The experimental results show that the proposed model has a faster convergence speed and higher accuracy, which will provide a valuable reference for decision making and the management of enterprise collaboration.