In the era of the swift advancement of information technology, it is extremely urgent for enterprise financial management systems to undergo digital upgrading. This research devises a comprehensive enterprise financial management system founded on big – data technology. This system incorporates two crucial subsystems: financial decision – making support and financial risk early – warning.Regarding financial decision – making support, through the utilization of FP – growth association rules and clustering algorithms, the indicators that influence the financial standing of enterprises are investigated and classified. For financial risk early – warning, a model is put forward, which is based on the optimization of a BP neural network by the particle swarm algorithm (PSO). The particle swarm algorithm is employed to search for the optimal initial weights and thresholds of the BP neural network.Moreover, the DEA – Malmquist approach is utilized to examine the impact on the enhancement of capital efficiency after the implementation of the digital financial management system in enterprises. The findings of the empirical research indicate that the overall prediction accuracy of the model attains 89.23%, suggesting that the model presented in this paper holds considerable practical worth.From 2019 to 2020, the efficiency of fund utilization has been increased by 13.06%. This reveals the substantial positive influence of digital transformation on improving the efficiency of fund utilization, and offers theoretical backing and methodological strategies for the digital transformation of the financial management of relevant enterprises.
