基于广义回归神经网络的单位运营状况分类

单位的运营状况会直接影响股东和广大人民的利益,针对运营状况可以使用广义回归神经网络进行分类。由于广义回归神经网络中径向基函数的扩展参数Spread的选取会导致分类的准确率,提出了一种果蝇优化算法优化参数Spread的分类模型。充分利用了果蝇优化算法的寻优能力,将优化后的参数代入到广义回归神经网络中对单位的财务数据进行运营状况的分类。结果表明,与广义回归神经网络做比较,优化后的网络模型对数据的分类可以达到很高的准确率,在相关领域的分类上有非常大的实用性。

Classification of Company Operation Condition Based on the Generalized Regression Neural Network

The operation of the company will directly affect the interests of the shareholders and the general people and the use of generalized regression neural network to classify in view of the operational situation is put forward. According to the selection of the radial basis function of the extended parameter spread in the generalized regression neural network may lead to the accuracy of classification,a classification model based on fruit fly optimization algorithm to optimize the generalized regression neural network is proposed. Make full use of the fruit fly optimization algorithm global search optimization ability and the optimized parameters are substituted into the generalized regression neural network to classify the company's bankruptcy data. The experimental results show that compared to the generalized regression neural network,the optimized network model has a better forecasting accuracy, and it has a great practical value in the prediction and classification of related fields.