@inproceedings{kirtac-germano-2025-leveraging,
title = "Leveraging {LLM}-based sentiment analysis for portfolio optimization with proximal policy optimization",
author = "Kirtac, Kemal and
Germano, Guido",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Lu, Xing Han and
Dziri, Nouha and
Murty, Shikhar and
Lacoste, Alexandre",
booktitle = "Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.realm-1.12/",
doi = "10.18653/v1/2025.realm-1.12",
pages = "160--169",
ISBN = "979-8-89176-264-0",
abstract = "Reinforcement learning (RL) offers adaptive solutions to portfolio optimization, yet standard methods such as proximal policy optimization (PPO) rely exclusively on historical price data and overlook the impact of investor sentiment. We introduce sentiment-augmented PPO (SAPPO), a reinforcement learning framework that incorporates real-time sentiment signals extracted from Refinitiv financial news. Daily sentiment scores are generated using LLaMA 3.3. SAPPO integrates these signals into the PPO advantage function via a sentiment-weighted term, enabling allocation strategies that respond to both price movements and market sentiment. Experiments on a three-asset portfolio demonstrate that SAPPO increases the Sharpe ratio from 1.55 to 1.90 and reduces drawdowns relative to PPO. The optimal configuration uses a sentiment influence parameter $\lambda = 0.1$, as validated through ablation studies and statistically significant $t$-tests ($p < 0.001$). These findings show that sentiment-aware reinforcement learning improves trading performance and offers a robust alternative to purely price-based strategies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kirtac-germano-2025-leveraging">
<titleInfo>
<title>Leveraging LLM-based sentiment analysis for portfolio optimization with proximal policy optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Kirtac</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Germano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikhar</namePart>
<namePart type="family">Murty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Lacoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-264-0</identifier>
</relatedItem>
<abstract>Reinforcement learning (RL) offers adaptive solutions to portfolio optimization, yet standard methods such as proximal policy optimization (PPO) rely exclusively on historical price data and overlook the impact of investor sentiment. We introduce sentiment-augmented PPO (SAPPO), a reinforcement learning framework that incorporates real-time sentiment signals extracted from Refinitiv financial news. Daily sentiment scores are generated using LLaMA 3.3. SAPPO integrates these signals into the PPO advantage function via a sentiment-weighted term, enabling allocation strategies that respond to both price movements and market sentiment. Experiments on a three-asset portfolio demonstrate that SAPPO increases the Sharpe ratio from 1.55 to 1.90 and reduces drawdowns relative to PPO. The optimal configuration uses a sentiment influence parameter Ĺ‚ambda = 0.1, as validated through ablation studies and statistically significant t-tests (p < 0.001). These findings show that sentiment-aware reinforcement learning improves trading performance and offers a robust alternative to purely price-based strategies.</abstract>
<identifier type="citekey">kirtac-germano-2025-leveraging</identifier>
<identifier type="doi">10.18653/v1/2025.realm-1.12</identifier>
<location>
<url>https://aclanthology.org/2025.realm-1.12/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>160</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging LLM-based sentiment analysis for portfolio optimization with proximal policy optimization
%A Kirtac, Kemal
%A Germano, Guido
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Lu, Xing Han
%Y Dziri, Nouha
%Y Murty, Shikhar
%Y Lacoste, Alexandre
%S Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-264-0
%F kirtac-germano-2025-leveraging
%X Reinforcement learning (RL) offers adaptive solutions to portfolio optimization, yet standard methods such as proximal policy optimization (PPO) rely exclusively on historical price data and overlook the impact of investor sentiment. We introduce sentiment-augmented PPO (SAPPO), a reinforcement learning framework that incorporates real-time sentiment signals extracted from Refinitiv financial news. Daily sentiment scores are generated using LLaMA 3.3. SAPPO integrates these signals into the PPO advantage function via a sentiment-weighted term, enabling allocation strategies that respond to both price movements and market sentiment. Experiments on a three-asset portfolio demonstrate that SAPPO increases the Sharpe ratio from 1.55 to 1.90 and reduces drawdowns relative to PPO. The optimal configuration uses a sentiment influence parameter Ĺ‚ambda = 0.1, as validated through ablation studies and statistically significant t-tests (p < 0.001). These findings show that sentiment-aware reinforcement learning improves trading performance and offers a robust alternative to purely price-based strategies.
%R 10.18653/v1/2025.realm-1.12
%U https://aclanthology.org/2025.realm-1.12/
%U https://doi.org/10.18653/v1/2025.realm-1.12
%P 160-169
Markdown (Informal)
[Leveraging LLM-based sentiment analysis for portfolio optimization with proximal policy optimization](https://aclanthology.org/2025.realm-1.12/) (Kirtac & Germano, REALM 2025)
ACL