Financial Early Warning of Listed Companies Based on Fireworks Algorithm Optimized Back-Propagation Neural Network

Aiming at the problems of slow convergence speed, easy to fall into local optimum and poor robustness based on BP neural network (Back-Propagation), a fireworks algorithm is proposed as a pre-device of neural network model to optimize the initial value and threshold of the network input, and then The error is corrected by the BP neural network algorithm to obtain an optimal value. This method improves the prediction accuracy of the network. The empirical research shows that the accuracy of the financial distress prediction of the optimization model is higher than that of the traditional BP neural network model.