Research on multi-objective optimization model of enterprise performance evaluation based on big data

]In the enterprise performance evaluation driven by big data, how to effectively extract key features from massive data and carry out multi-objective optimization is an important topic of current research. In this paper, an innovative Recursive Feature Multi-Objective Evolutionary (RFMOE) algorithm is proposed, which combines the advantages of recursive feature elimination (RFE) and decomposition based multi-objective evolutionary algorithm (MOEA/D). In the multi-objective optimization model of enterprise performance evaluation based on big data, RFMOE first utilizes the iterative feature selection mechanism of RFE to effectively eliminate redundant and unimportant features, reduce data dimensions, and improve model efficiency. Then, the multi-objective optimization problem is decomposed into multiple single-objective subproblems by MOEA/D, and the information exchange of adjacent subproblems is used to optimize the solution process to obtain a set of Pareto optimal solutions. Finally, by comparing the model architecture with the traditional model, the results show that RFMOE has significant advantages in improving the evaluation accuracy, enhancing the robustness of the model and improving the decision-making efficiency, which provides a powerful tool for the performance management and strategic planning of enterprises. The feasibility and effectiveness of this model in enterprise performance evaluation are proved.