@inproceedings{becquin-esmeir-2023-semantic,
title = "Semantic Similarity Covariance Matrix Shrinkage",
author = "Becquin, Guillaume and
Esmeir, Saher",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.668",
doi = "10.18653/v1/2023.findings-emnlp.668",
pages = "9977--9992",
abstract = "An accurate estimation of the covariance matrix is a critical component of many applications in finance, including portfolio optimization. The sample covariance suffers from the curse of dimensionality when the number of observations is in the same order or lower than the number of variables. This tends to be the case in portfolio optimization, where a portfolio manager can choose between thousands of stocks using historical daily returns to guide their investment decisions. To address this issue, past works proposed linear covariance shrinkage to regularize the estimated matrix. While effective, the proposed methods relied solely on historical price data and thus ignored company fundamental data. In this work, we propose to utilise semantic similarity derived from textual descriptions or knowledge graphs to improve the covariance estimation. Rather than using the semantic similarity directly as a biased estimator to the covariance, we employ it as a shrinkage target. The resulting covariance estimators leverage both semantic similarity and recent price history, and can be readily adapted to a broad range of financial securities. The effectiveness of the approach is demonstrated for a period including diverse market conditions and compared with the covariance shrinkage prior art.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="becquin-esmeir-2023-semantic">
<titleInfo>
<title>Semantic Similarity Covariance Matrix Shrinkage</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Becquin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saher</namePart>
<namePart type="family">Esmeir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An accurate estimation of the covariance matrix is a critical component of many applications in finance, including portfolio optimization. The sample covariance suffers from the curse of dimensionality when the number of observations is in the same order or lower than the number of variables. This tends to be the case in portfolio optimization, where a portfolio manager can choose between thousands of stocks using historical daily returns to guide their investment decisions. To address this issue, past works proposed linear covariance shrinkage to regularize the estimated matrix. While effective, the proposed methods relied solely on historical price data and thus ignored company fundamental data. In this work, we propose to utilise semantic similarity derived from textual descriptions or knowledge graphs to improve the covariance estimation. Rather than using the semantic similarity directly as a biased estimator to the covariance, we employ it as a shrinkage target. The resulting covariance estimators leverage both semantic similarity and recent price history, and can be readily adapted to a broad range of financial securities. The effectiveness of the approach is demonstrated for a period including diverse market conditions and compared with the covariance shrinkage prior art.</abstract>
<identifier type="citekey">becquin-esmeir-2023-semantic</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.668</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.668</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>9977</start>
<end>9992</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Similarity Covariance Matrix Shrinkage
%A Becquin, Guillaume
%A Esmeir, Saher
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F becquin-esmeir-2023-semantic
%X An accurate estimation of the covariance matrix is a critical component of many applications in finance, including portfolio optimization. The sample covariance suffers from the curse of dimensionality when the number of observations is in the same order or lower than the number of variables. This tends to be the case in portfolio optimization, where a portfolio manager can choose between thousands of stocks using historical daily returns to guide their investment decisions. To address this issue, past works proposed linear covariance shrinkage to regularize the estimated matrix. While effective, the proposed methods relied solely on historical price data and thus ignored company fundamental data. In this work, we propose to utilise semantic similarity derived from textual descriptions or knowledge graphs to improve the covariance estimation. Rather than using the semantic similarity directly as a biased estimator to the covariance, we employ it as a shrinkage target. The resulting covariance estimators leverage both semantic similarity and recent price history, and can be readily adapted to a broad range of financial securities. The effectiveness of the approach is demonstrated for a period including diverse market conditions and compared with the covariance shrinkage prior art.
%R 10.18653/v1/2023.findings-emnlp.668
%U https://aclanthology.org/2023.findings-emnlp.668
%U https://doi.org/10.18653/v1/2023.findings-emnlp.668
%P 9977-9992
Markdown (Informal)
[Semantic Similarity Covariance Matrix Shrinkage](https://aclanthology.org/2023.findings-emnlp.668) (Becquin & Esmeir, Findings 2023)
ACL
- Guillaume Becquin and Saher Esmeir. 2023. Semantic Similarity Covariance Matrix Shrinkage. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9977–9992, Singapore. Association for Computational Linguistics.