Assessment Model for the Degree of Digital Enterprises based on a GA-BP Neural Network

Abstract

Enterprises are the microcosm of economy and society. In the background of the booming digital economy, the digital development of enterprises will directly affect the digitalization process of society, so it is crucial to assess the degree of digital enterprises. Meanwhile, owing to the shortcomings of the BP neural network model, such as easy to cannot achieve global optimum and relatively slow convergence, genetic algorithm was used to optimize its initial weights and thresholds in this paper. After that, we constructed a comprehensive index for the degree of digitization of the enterprise and evaluated it separately with the pre- and post-optimization models that had been trained. And the experiment proved that the optimized neural network model was better than the pre-optimized neural network model in terms of prediction accuracy and convergence speed. All in all, it appears that GA-BP neural network has good application prospects in the field of enterprise digital evaluation.