Enterprise financial early warning based on improved particle swarm optimization algorithm and data mining

Abstract

In the Internet era, enterprises are surrounded by massive information, and the information ability of effective organization is becoming more and more important for modern enterprise management. How to continuously dig into the economic data formed in the operation of enterprises, and then discover the intelligence with the effect of financial risk warning, has become an urgent problem to be dealt with. Sophisticated data mining techniques continue to evolve, creating a clear sense of direction for dealing with this problem. Like most collective intelligence algorithms, optimized particle swarm optimization is a typical algorithm for optimizing collective intelligence. Usually, a set of solutions is started randomly, but these solutions are also updated through continuous repetition. Therefore, this paper, aiming at this problem, has carried on a series of improvement methods, improved the particle property algorithm and analyzed the particle swarm optimization algorithm, at the same time, clarified its long time in the elimination stage and can not be applied to some problems. Therefore, how to design improved strategies for swarm intelligence algorithms, especially better particle walking algorithms and their variants, to further improve the solving quality and efficiency of such algorithms when solving complex optimization problems is also a research focus in this field.