SOM神经网络聚类算法在高校经费监管领域的实践与应用

The Practice and Application of SOM Neural Network Clustering Algorithm in the Field of University Funding Supervision

随着我国教育经费规模不断扩大,违法违纪使用教育经费行为时有发生。高校财务业务数据量大、数据维度多,致使传统人工稽核无法及时发现报销中的异常行为。自组织映射(Self Organizing Maps,SOM)神经网络聚类算法具有无监督的特点,可以快速发现异常报销行为。基于此,介绍了SOM神经网络聚类算法的原理,并分析了SOM神经网络聚类算法在高校经费监管领域的应用。

With the expansion of the scale of education funds,illegal and undisciplined use of education funds occurs sometimes.The Self Organizing Maps(SOM)neural network clustering algorithm can quickly and efficiently detect the abnormal reimbursement behavior with its unsupervised feature.Based on this,this paper introduces the principle of SOM neural network clustering algorithm,and conducts a practical test of SOM neural network clustering algorithm in the field of university funding supervision.