基于岭熵最大化模型的银行间网络重构
Reconstruction of Interbank Network using Ridge Entropy Maximization Model
摘要：
考虑到网络的稀疏性，提出了一种基于熵最大化的网络重构模型。我们使用开发的重构模型，根据2000年至2016年各银行资产负债表的财务数据，重构了日本的银行间网络。观测到的银行间网络的稀疏性被成功地再现。我们通过计算重要的网络属性来检查重建的银行间网络的特性。我们得到以下特征，这与先前已知的程式化事实是一致的。虽然我们没有引入产生核心和外围结构的机制，但我们施加了约束条件来考虑稀疏性，即除了主要的商业银行之外，同一银行类别内没有交易，核心和外围结构已经自发出现。我们使用PageRank和度的值来确定每个社区中的主要节点，以检查每个银行类别的角色变化。银行角色的变化被认为是日本银行从2013年4月开始实施定量和定性货币宽松政策的结果。
英文摘要：
We develop a network reconstruction model based on entropy maximization considering the sparsity of networks. We reconstruct the interbank network in Japan from financial data in individual banks' balance sheets using the developed reconstruction model from 2000 to 2016. The observed sparsity of the interbank network is successfully reproduced. We examine the characteristics of the reconstructed interbank network by calculating important network attributes. We obtain the following characteristics, which are consistent with the previously known stylized facts. Although we do not introduce the mechanism to generate the core and peripheral structure, we impose the constraints to consider the sparsity that is no transactions within the same bank category except for major commercial banks, the core and peripheral structure has spontaneously emerged. We identify major nodes in each community using the value of PageRank and degree to examine the changing role of each bank category. The observed changing role of banks is considered a result of the quantitative and qualitative monetary easing policy started by the Bank of Japan in April 2013.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
