The objective of the research is to analyze the ability of the artificial neural network model developed to forecast the credit risk of a panel of Italian manufacturing companies. In a theoretical point of view, this ...The objective of the research is to analyze the ability of the artificial neural network model developed to forecast the credit risk of a panel of Italian manufacturing companies. In a theoretical point of view, this paper introduces a litera-ture review on the application of artificial intelligence systems for credit risk management. In an empirical point of view, this research compares the architecture of the artificial neural network model developed in this research to an-other one, built for a research conducted in 2004 with a similar panel of companies, showing the differences between the two neural network models.展开更多
为了降低银行的放贷风险,在构建商业银行个人住房贷款信用风险评价指标基础上,采用机器学习原理中的近似支持向量机(Proximal Support Vector Machines,PSVM)模型对某商业银行西安市场的个人住房贷款借款人数据进行实证分析,研究中个人...为了降低银行的放贷风险,在构建商业银行个人住房贷款信用风险评价指标基础上,采用机器学习原理中的近似支持向量机(Proximal Support Vector Machines,PSVM)模型对某商业银行西安市场的个人住房贷款借款人数据进行实证分析,研究中个人住房贷款借款人的各项指标作为属性矩阵,借款人是否违约作为判别矩阵,利用260个样本的训练集获得最优超平面,再对40个样本的测试集进行预测,结果表明PSVM模型在预测商业银行个人住房贷款信用风险时的正确率达到了87.5%.展开更多
文摘The objective of the research is to analyze the ability of the artificial neural network model developed to forecast the credit risk of a panel of Italian manufacturing companies. In a theoretical point of view, this paper introduces a litera-ture review on the application of artificial intelligence systems for credit risk management. In an empirical point of view, this research compares the architecture of the artificial neural network model developed in this research to an-other one, built for a research conducted in 2004 with a similar panel of companies, showing the differences between the two neural network models.
文摘为了降低银行的放贷风险,在构建商业银行个人住房贷款信用风险评价指标基础上,采用机器学习原理中的近似支持向量机(Proximal Support Vector Machines,PSVM)模型对某商业银行西安市场的个人住房贷款借款人数据进行实证分析,研究中个人住房贷款借款人的各项指标作为属性矩阵,借款人是否违约作为判别矩阵,利用260个样本的训练集获得最优超平面,再对40个样本的测试集进行预测,结果表明PSVM模型在预测商业银行个人住房贷款信用风险时的正确率达到了87.5%.