基于动量BP神经网络的PFI项目风险评价  

Risk Evaluation of PFI Project Based on Momentum BP Neural Network

作　　者：杨金星[1] 刘宁[1] 刘亚臣[1] 

机构地区：[1]沈阳建筑大学管理学院,辽宁沈阳110168

出　　处：《沈阳建筑大学学报（社会科学版）》2013年第2期202-204,共3页Journal of Shenyang Jianzhu University:Social Science

基　　金：住房和城乡建设部科学技术计划项目(2010-R5-13)

摘　　要：运用BP(Back Propagation)神经网络技术,采用动量BP算法,构建风险评价模型。对PFI项目存在的系统风险及非系统风险进行划分,建立包含政治、法律、金融、生产、市场、信用以及环保等风险的PFI项目风险评价指标体系。对专家组打分获得的训练样本进行训练,得到可靠性验证的训练网络。最后,将某PFI项目打分结果输入已训练好的网络,判定该PFI项目风险等级,为私营公司的决策提供参考依据。This paper applies BP Neural Network technology, uses momentum BP algorithm, constructs risk evaluation model. It divides systematic and unsystematic risks in PFI project, establishes risk evaluation in- dex system containing political risk, legal risk, financial risk, production risk, market risk, credit risk and the environmental protection of PFI project. It trains the training samples which the expert group has graded, gets the reliability verified training network. Finally, it inputs the score results to the network that has trained,judges the risk level of the given PFI project, provides the references for private company＇ s deci- sion.

关 键 词：PFI项目 动量BP神经网络 评价指标体系 风险评价 

分 类 号：F407.9[经济管理—产业经济]