摘要
文章梳理了系统性金融风险理论基础和形成原因,从外部经济、大连宏观经济、大连金融机构3个维度选取了10个指标,构建了大连系统性金融风险预警指标体系。应用大数据方法中的主成分分析、K-均值聚类对指标进行了降维与分类,并使用大连2005—2020年的相关指标数据对径向基神经网络模型进行训练和测试,建立了一个预测系统性金融风险的模型。在训练完成后,将大连2021年的指标数据作为输入数据,具体预测了大连2022年的系统性金融风险状态。
By sorting out the theoretical basis and causes of systemic financial risks,this paper tries to construct a warning indicator system of systemic financial risk of Dalian by selecting 10 indicators from three dimensions:external economy,macro-economy,and financial institutions.Principal component analysis and K-means clustering in big data were employed to downscale and categorize these indicators,and the radial basis function neural network model was trained and tested using relevant indicator data from 2005 to 2020.After the completion of the training,the indicator data of Dalian in 2021 was used as input data to predict the systemic financial risk in 2022.
作者
李艳玲
陈丹丹
Li Yanling;Chen Dandan(Dalian University of Finance and Economics,Dalian 116622)
出处
《中阿科技论坛（中英文）》
2023年第9期67-70,共4页
China-Arab States Science and Technology Forum
基金
辽宁省社会科学规划基金项目“大数据时代多源异构数据融合下辽宁上市公司财务危机预测研究”(L20BGL003)。
关键词
系统性金融风险
主成分分析
径向基神经网络
大连
Systemic financial risk
Principal component analysis
Radial basis function neural network
Dalian
