@inproceedings{li-etal-2024-large-language,
title = "Can Large Language Models Mine Interpretable Financial Factors More Effectively? A Neural-Symbolic Factor Mining Agent Model",
author = "Li, Zhiwei and
Song, Ran and
Sun, Caihong and
Xu, Wei and
Yu, Zhengtao and
Wen, Ji-Rong",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.233",
doi = "10.18653/v1/2024.findings-acl.233",
pages = "3891--3902",
abstract = "Finding interpretable factors for stock returns is the most vital issue in the empirical asset pricing domain. As data-driven methods, existing factor mining models can be categorized into symbol-based and neural-based models. Symbol-based models are interpretable but inefficient, while neural-based approaches are efficient but lack interpretability. Hence, mining interpretable factors effectively presents a significant challenge. Inspired by the success of Large Language Models (LLMs) in various tasks, we propose a FActor Mining Agent (FAMA) model that enables LLMs to integrate the strengths of both neural and symbolic models for factor mining. In this paper, FAMA consists of two main components: Cross-Sample Selection (CSS) and Chain-of-Experience (CoE). CSS addresses the homogeneity challenges in LLMs during factor mining by assimilating diverse factors as in-context samples, whereas CoE enables LLMs to leverage past successful mining experiences, expediting the mining of effective factors. Experimental evaluations on real-world stock market data demonstrate the effectiveness of our approach by surpassing the SOTA RankIC by 0.006 and RankICIR by 0.105 in predicting S{\&}P 500 returns. Furthermore, the investment simulation shows that our model can achieve superior performance with an annualized return of 38.4{\%} and a Sharpe ratio of 667.2{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-large-language">
<titleInfo>
<title>Can Large Language Models Mine Interpretable Financial Factors More Effectively? A Neural-Symbolic Factor Mining Agent Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ran</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caihong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengtao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-Rong</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Finding interpretable factors for stock returns is the most vital issue in the empirical asset pricing domain. As data-driven methods, existing factor mining models can be categorized into symbol-based and neural-based models. Symbol-based models are interpretable but inefficient, while neural-based approaches are efficient but lack interpretability. Hence, mining interpretable factors effectively presents a significant challenge. Inspired by the success of Large Language Models (LLMs) in various tasks, we propose a FActor Mining Agent (FAMA) model that enables LLMs to integrate the strengths of both neural and symbolic models for factor mining. In this paper, FAMA consists of two main components: Cross-Sample Selection (CSS) and Chain-of-Experience (CoE). CSS addresses the homogeneity challenges in LLMs during factor mining by assimilating diverse factors as in-context samples, whereas CoE enables LLMs to leverage past successful mining experiences, expediting the mining of effective factors. Experimental evaluations on real-world stock market data demonstrate the effectiveness of our approach by surpassing the SOTA RankIC by 0.006 and RankICIR by 0.105 in predicting S&P 500 returns. Furthermore, the investment simulation shows that our model can achieve superior performance with an annualized return of 38.4% and a Sharpe ratio of 667.2%.</abstract>
<identifier type="citekey">li-etal-2024-large-language</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.233</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.233</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>3891</start>
<end>3902</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Large Language Models Mine Interpretable Financial Factors More Effectively? A Neural-Symbolic Factor Mining Agent Model
%A Li, Zhiwei
%A Song, Ran
%A Sun, Caihong
%A Xu, Wei
%A Yu, Zhengtao
%A Wen, Ji-Rong
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F li-etal-2024-large-language
%X Finding interpretable factors for stock returns is the most vital issue in the empirical asset pricing domain. As data-driven methods, existing factor mining models can be categorized into symbol-based and neural-based models. Symbol-based models are interpretable but inefficient, while neural-based approaches are efficient but lack interpretability. Hence, mining interpretable factors effectively presents a significant challenge. Inspired by the success of Large Language Models (LLMs) in various tasks, we propose a FActor Mining Agent (FAMA) model that enables LLMs to integrate the strengths of both neural and symbolic models for factor mining. In this paper, FAMA consists of two main components: Cross-Sample Selection (CSS) and Chain-of-Experience (CoE). CSS addresses the homogeneity challenges in LLMs during factor mining by assimilating diverse factors as in-context samples, whereas CoE enables LLMs to leverage past successful mining experiences, expediting the mining of effective factors. Experimental evaluations on real-world stock market data demonstrate the effectiveness of our approach by surpassing the SOTA RankIC by 0.006 and RankICIR by 0.105 in predicting S&P 500 returns. Furthermore, the investment simulation shows that our model can achieve superior performance with an annualized return of 38.4% and a Sharpe ratio of 667.2%.
%R 10.18653/v1/2024.findings-acl.233
%U https://aclanthology.org/2024.findings-acl.233
%U https://doi.org/10.18653/v1/2024.findings-acl.233
%P 3891-3902
Markdown (Informal)
[Can Large Language Models Mine Interpretable Financial Factors More Effectively? A Neural-Symbolic Factor Mining Agent Model](https://aclanthology.org/2024.findings-acl.233) (Li et al., Findings 2024)
ACL