数据挖掘在检测农业补贴中欺诈行为的应用--基于异常检测与神经网络模型

摘要

随着国家对农业发展扶持力度的不断加大，农业补贴申请资金得到提高的同时，其种类也在逐渐扩充.因此，如何检测农业补贴申请中的欺诈行为是一项值得关注的研究课题.通过对clementine 12.0中的案例数据分别构建异常检测和神经网络模型，对农业补贴申请记录中的欺诈行为进行检测，并借助 clementine 12.0的可视化实验平台直观、有效地观察检测结果.实验结果表明：提出的方法可以明显地提高检测欺诈行为的效率及准确率，具有一定的启发和借鉴意义.%With the increased investment on agriculture,the fund categories of agricultural subsidy are to be improved and enlarged. Therefore,it is an interesting research topic to detect frauds in agricultural subsidy. The author establishes the anomaly detection and neural network models to detect frauds in agricultural subsidy with the case database of clementine 12 . 0 . It can intuitively and effectively observe the results by visualized experi-mental platform. The experimental results show that the method proposed in this paper can improve the efficiency and accuracy of detecting frauds,and has some reference significance.