@inproceedings{guo-hauptmann-2024-fine,
title = "Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow",
author = "Guo, Tian and
Hauptmann, Emmanuel",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.77",
pages = "1028--1045",
abstract = "Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks.This paper explores fine-tuning LLMs for predicting stock returns with financial newsflow.Return prediction is fundamental for subsequent tasks like portfolio construction and optimization in quantitative investing. We formulate the model to include a text representation and forecasting modules. We propose to compare the encoder-only and decoder-only LLMs, considering they generate text representations in distinct ways.The impact of these different representations on return forecasting remains an open question.Meanwhile, we compare two simple methods of integrating LLMs{'} token-level representations into the forecasting module.The experiments on real investment universes reveal that:(1) aggregated representations from LLMs{'} token-level embeddings generally produce return predictions that enhance the performance of long-only and long-short portfolios;(2) in the relatively large investment universe, the decoder LLMs-based prediction model leads to stronger portfolios, whereas in the small universes, there are no consistent winners;(3) return predictions derived from LLMs{'} text representations are a strong signal for portfolio construction, outperforming conventional sentiment scores.These findings shed light on developing suitable LLM fine-tuning methods for return prediction-based portfolio construction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-hauptmann-2024-fine">
<titleInfo>
<title>Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Hauptmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoţiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks.This paper explores fine-tuning LLMs for predicting stock returns with financial newsflow.Return prediction is fundamental for subsequent tasks like portfolio construction and optimization in quantitative investing. We formulate the model to include a text representation and forecasting modules. We propose to compare the encoder-only and decoder-only LLMs, considering they generate text representations in distinct ways.The impact of these different representations on return forecasting remains an open question.Meanwhile, we compare two simple methods of integrating LLMs’ token-level representations into the forecasting module.The experiments on real investment universes reveal that:(1) aggregated representations from LLMs’ token-level embeddings generally produce return predictions that enhance the performance of long-only and long-short portfolios;(2) in the relatively large investment universe, the decoder LLMs-based prediction model leads to stronger portfolios, whereas in the small universes, there are no consistent winners;(3) return predictions derived from LLMs’ text representations are a strong signal for portfolio construction, outperforming conventional sentiment scores.These findings shed light on developing suitable LLM fine-tuning methods for return prediction-based portfolio construction.</abstract>
<identifier type="citekey">guo-hauptmann-2024-fine</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-industry.77</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1028</start>
<end>1045</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow
%A Guo, Tian
%A Hauptmann, Emmanuel
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F guo-hauptmann-2024-fine
%X Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks.This paper explores fine-tuning LLMs for predicting stock returns with financial newsflow.Return prediction is fundamental for subsequent tasks like portfolio construction and optimization in quantitative investing. We formulate the model to include a text representation and forecasting modules. We propose to compare the encoder-only and decoder-only LLMs, considering they generate text representations in distinct ways.The impact of these different representations on return forecasting remains an open question.Meanwhile, we compare two simple methods of integrating LLMs’ token-level representations into the forecasting module.The experiments on real investment universes reveal that:(1) aggregated representations from LLMs’ token-level embeddings generally produce return predictions that enhance the performance of long-only and long-short portfolios;(2) in the relatively large investment universe, the decoder LLMs-based prediction model leads to stronger portfolios, whereas in the small universes, there are no consistent winners;(3) return predictions derived from LLMs’ text representations are a strong signal for portfolio construction, outperforming conventional sentiment scores.These findings shed light on developing suitable LLM fine-tuning methods for return prediction-based portfolio construction.
%U https://aclanthology.org/2024.emnlp-industry.77
%P 1028-1045
Markdown (Informal)
[Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow](https://aclanthology.org/2024.emnlp-industry.77) (Guo & Hauptmann, EMNLP 2024)
ACL