With the arrival of the digital era, how enterprises can promote their financial performance through the implementation of digital transformation has become a hot issue. This paper establishes an enterprise financial performance evaluation system based on fuzzy theory and BP neural network. First, a reasonable neural network structure including the number of network layers, the number of nodes in the hidden layer, the training method and other related parameters are set, and then the adaptive step maximum gradient descent method is applied to train and test the BP neural network, and the constructed fuzzy system, which is combined with the BP neural network, is applied to the evaluation of corporate financial performance. Finally, taking Company Q in the traditional Chinese medicine industry as the research object, the construction of the financial performance evaluation index system is completed, and the four common factors representing 85.692% of the information of the original variables are extracted by using the factor analysis method to complete the scientific description of the enterprise’s financial performance management level. The evaluation model based on fuzzy logic and BP neural network achieves an average prediction accuracy of more than 95% for the test samples, realizes excellent financial performance optimization and innovation, and puts forward comprehensive measures such as setting up internal enterprise financial performance management values, exerting the performance appraisal mechanism and guiding the systematization of performance evaluation, which to a certain extent improves the enterprise performance management system.
