Optimization Algorithm for Enterprise Decision Making Based on Big Data Fusion

Abstract

The rise of big data technology has opened up new horizons for optimizing enterprise decision-making. It can not only process traditional structured data but also deeply explore valuable information in semi-structured and unstructured data. In this era, this article is committed to building an enterprise decision optimization algorithm that integrates computer-aided and big-data technology. We will apply the constructed decision optimization algorithm to the financial risk prediction model and verify its superiority in financial risk prediction through empirical research. The accuracy of this method is 20.01% higher than that of the Support Vector Machine (SVM) algorithm, and the error is reduced by 42.77%. In terms of model stability, backpropagation neural networks (BPNN) have significantly higher stability than other methods. This means that the model constructed in this article can operate more stably in practical applications, providing more reliable support for financial risk management. In the future, we will further explore and study how to apply this model to a wider range of financial scenarios.