应用果蝇优化算法优化广义回归神经网络进行企业经营绩效评估

Using Fruit Fly Optimization Algorithm Optimized General Regression Neural Network to Construct the Operating Performance of Enterprises Model

近年来,台湾受到美国次贷风暴及欧洲债信的影响,许多大型企业瓦解的事件陆续发生,因此,公司管理阶层有必要好好地检视公司的财务状况,及早防范公司可能面临的经营风险。文章按照财务五力搜集台湾企业财务比率资料,根据活动力、稳定力与收益力进行灰关联分析,再将分析结果按照灰关联度进行排序,以了解各企业的经营绩效排名;然后采用果蝇优化算法优化广义回归神经网络、一般广义回归神经网络与多元回归模型,进行企业经营绩效侦测模型的建构,以供研究人员及公司管理阶层参考。分析结果显示,应用果蝇优化算法优化广义回归神经网络在企业经营绩效侦测模型的预测误差有很好的收敛结果,也有很好的分类预测能力。

In recent years, influenced by european debt, bankruptcy or debt-raising risk occurs in many enterprises at Taiwan,sometime,even settlement default might occur at the stock market. Therefore, the manager level of an enterprise really has to inspect the financial situation of an en- terprise well. In this article, financial five forces are followed to collect the financial ratio data from enterprises, in the mean time, grey relational analysis is performed on financial five forces, then the analysis results are ranked according to grey relational grade so as to understand the op- erating performance ranking of each enterprise; then fruit fly optimization algorithm optimized general regression neural network,general regression neural network and multiple regression are used to construct respectively operating performance of enterprises model. From the analytical re- sult,we have found that in operating performance of enterprises model,the RMSE value of fruit fly optimization algorithm optimized general regression neural network model has very good con- vergent result and classification forecast capability.