基于BA-BP算法的企业经营状况评价模型

An Evaluation Model of Enterprises' Management Condition Based on BA-BP Algorithm

传统BP神经网络参数的选取是随机的,这样易使网络陷入局部最优,针对这一缺点,提出了利用蝙蝠算法优化BP网络参数的改进算法——蝙蝠-BP算法(BA-BP),并将其应用于企业经营状况的评价研究中。建立了基于BA-BP算法的企业经营状况的评价模型,运用测试样本对该评价模型与传统BP模型的预测效果进行了对比,仿真结果表明:BA-BP算法的预测精度比传统BP神经网络的预测精度高,所以基于BA-BP算法的评价模型能够有效地评价企业的经营状况。

The traditional BP neural network＇ s parameters are selected at random, and it is easy to make the network into a local optimum. Aimed at the shortcoming,the paper put forward an improved algorithm：BA-BP algorithm which uses the bat algorithm to optimize BP network＇ s parameters, and applied the algorithm to the evaluation of the business situation. An evaluation model of enterprises＇ business status based on BA-BP algorithm was set up. Finally, the prediction effect of BABP model was compared to the traditional BP model with the test samples. The simulation results show that the prediction accuracy of BA-BP is higher than the traditional BP neural network, so the evaluation model based on BA-BP algorithm can forecast the enterprises＇ business status effectively.