会议论文

Learning Undirected Graphs in Financial Markets 收藏

学习金融市场中的无向图

机构暂未开通该资源的服务权限，如有疑问请联系图书馆。发布源

作者

José Vinícius de Miranda Cardoso[1];Daniel P. Palomar[1]

作者单位

[1]The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong

关键词

Computers;Laplace equations;Graphical models;Correlation;Computational modeling;Clustering algorithms;Indexes

关键词译文

计算机;拉普拉斯方程;图形模型;相关;计算建模;聚类算法;索引

发布日期

1-4 Nov. 2020

页码

741-745

DOI

10.1109/IEEECONF51394.2020.9443573

来源信息

Asilomar Conference on Signals, Systems & Computers ISBN：9781665447072, 2020年, 卷, 741-745页

摘要

We investigate the problem of learning undirected graphical models under Laplacian structural constraints from the point of view of financial market data. We show that Laplacian constraints have meaningful physical interpretations related to the market index factor and to conditional correlations between stocks. Those interpretations lead to a set of guidelines that users should be aware of when estimating graphs in financial markets. In addition, we propose algorithms to learn undirected graphs that account for stylized facts and tasks intrinsic to financial data such as non-stationarity and stock clustering.

摘要译文

从金融市场数据的角度来看，我们调查了拉普拉斯结构限制下学习无向图形模型的问题。我们表明拉普拉斯限制有与市场指数因素有意义的物理解释，以及股票之间有条件的相关性。这些解释导致了一系列准则，即在估计金融市场中的图表时应该了解用户。此外，我们提出了算法，以了解无向图的图形，该图占风格化事实和任务的金融数据，如非公平性和股票聚类。

José Vinícius de Miranda Cardoso[1];Daniel P. Palomar[1]. Learning Undirected Graphs in Financial Markets[C]//2020 54th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 1-4 Nov. 2020, US: IEEE, 2020: 741-745