Optimizing Financial Engineering Time Indicator Using Bionics Computation Algorithm and Neural Network Deep Learning

The present work aims to optimize the time index of financial engineering to improve the efficiency of financial decision-making. A Back Propagation Neural Network (BPNN) model is designed and optimized by the Ant Colony Algorithm (ACA) based on the bionic algorithm and Deep Learning (DL). After introducing the basic knowledge of neural networks and bionic algorithms, the advantages and disadvantages of the algorithms are integrated for maximal effects. Besides, ACA optimizes the weights and thresholds in the neural network in complex problems to reduce the relative error, enhance the stability and accuracy, and improve the classification speed of the BPNN model. The experimental results indicate that the classification accuracy of the ACA model is 91.3%, and the area under the receiver operating characteristic curve is 0.867. Moreover, the running time of BPNN based on ACA is 2.5 s, the error is 0.2, and the required number of iteration steps is 36 times, better than the test results of similar algorithms. These results demonstrate that the improved BPNN based on ACA has higher classification efficiency, better efficiency and smaller errors than the traditional BPNN. In terms of financial engineering decision-making, the time index of decision-making has been significantly improved, which is conducive to reducing the decision-making risk of financial institutions and has a positive effect on improving the overall operational efficiency of enterprises.

Automated summary

The present study aims to improve the efficiency of financial decision-making by optimizing the time index of financial engineering. By designing and optimizing a Back Propagation Neural Network model based on the Ant Colony Algorithm, the classification efficiency, stability, and accuracy have been improved while reducing errors. Experimental results show that the model achieves a classification accuracy of 91.3% with a running time of 2.5 seconds.