Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Intelligent Asset ManagementComputational Semantics for Asset Correlations

Intelligent Asset Management: Computational Semantics for Asset Correlations [This chapter explores the possibility to leverage semantic knowledge for robust estimation of correlations among financial assets. A graphical model for high-dimensional stochastic dependenceDependence modelinghigh-dimensional termed a “vine” structure, which is derived from copula theory, is introduced here. To model the prior semantic knowledge, we use a neural network-based language model to generate distributed semantic representations for financial documents. The semantic representations are used for computing similarities between the assets they respectively refer. The constructed dependence structure is experimented with real-world data. Results suggest that our semantic vineVinesemantic construction-based method is superior to the state-of-the-art covariance matrix estimation method, which is based on an arbitrary vine that at least guarantees robustness of the estimated covariance matrix. The effectiveness of using semantic vines for robust correlation estimation for Markowitz’s asset allocation modelMarkowitz model on a large scale of assets (up to 50 stocks) is also showed and discussed.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Intelligent Asset ManagementComputational Semantics for Asset Correlations

Part of the Socio-Affective Computing Book Series (volume 9)
Xing, Frank; Cambria, Erik; Welsch, Roy
Intelligent Asset Management — Nov 14, 2019
Download PDF
24 pages

Loading next page...
 
/lp/springer-journals/intelligent-asset-management-computational-semantics-for-asset-NZ7HZM0exG
Publisher
Springer International Publishing
Copyright
© Springer Nature Switzerland AG 2019
ISBN
978-3-030-30262-7
Pages
37 –61
DOI
10.1007/978-3-030-30263-4_4
Publisher site
See Chapter on Publisher Site

Abstract

[This chapter explores the possibility to leverage semantic knowledge for robust estimation of correlations among financial assets. A graphical model for high-dimensional stochastic dependenceDependence modelinghigh-dimensional termed a “vine” structure, which is derived from copula theory, is introduced here. To model the prior semantic knowledge, we use a neural network-based language model to generate distributed semantic representations for financial documents. The semantic representations are used for computing similarities between the assets they respectively refer. The constructed dependence structure is experimented with real-world data. Results suggest that our semantic vineVinesemantic construction-based method is superior to the state-of-the-art covariance matrix estimation method, which is based on an arbitrary vine that at least guarantees robustness of the estimated covariance matrix. The effectiveness of using semantic vines for robust correlation estimation for Markowitz’s asset allocation modelMarkowitz model on a large scale of assets (up to 50 stocks) is also showed and discussed.]

Published: Nov 14, 2019

Keywords: Asset allocation; Dependence modeling; Robust estimation; Doc2vec; Semantic vine; Correlation matrix; Machine learning

There are no references for this article.