A Comparative Study of Deep Reinforcement Learning Agents for Gold Trading with Technical Indicators and LLM-Filtered News Sentiment

Simple item page
dc.contributor.authorThanasarn, Thanapong
dc.contributor.authorAnuntachai, Anuntapat
dc.contributor.authorNetisopakul, Ponrudee
dc.date.accessioned2026-08-06T10:55:53Z
dc.date.available2026-08-06T10:55:53Z
dc.date.issued2026-06-16
dc.description.abstractIntegrating macroeconomic news into deep reinforcement learning (DRL) for daily gold (XAU/USD) trading remains challenging. This study implements a natural language processing pipeline using majority voting from three large language models (Llama-3.1-8B-Instruct, Qwen3-8B, and Gemma-3-12B-it) to filter articles from The New York Times from 2010 to 2024, yielding 592 relevant articles that are subsequently assigned sentiment scores using FinBERT. We evaluate A2C, PPO, and SAC agents in a FinRL and Stable-Baselines3 framework using a four-fold walk-forward expanding-window protocol and Optuna hyperparameter tuning. The models are compared under two feature settings: (1) six technical indicators only and (2) technical indicators combined with sentiment features. Results show that incorporating LLM-filtered sentiment can modestly improve trading performance for some agents. PPO with sentiment achieves the best average cumulative return (10.05%) and Sharpe ratio (0.74), compared with its indicator-only version (9.80%, 0.72), and slightly outperforms the Buy-and-Hold (B&H) baseline (9.58%, 0.71). A2C also improves with sentiment (9.50% to 9.90%), while SAC shows no improvement in this setting. These findings suggest that LLM-filtered sentiment provides a modest benefit for some DRL agents in daily gold trading in our experiments.
dc.identifier.citationIait 2026 14th International Conference on Advances in Information Technology, 2026
dc.identifier.doi10.1145/3816713.3818215
dc.identifier.other2-s2.0-105045271985
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/18199
dc.sourceIait 2026 14th International Conference on Advances in Information Technology
dc.subjectDeep reinforcement learning
dc.subjectgold trading
dc.subjectlarge language models
dc.subjectsentiment analysis
dc.titleA Comparative Study of Deep Reinforcement Learning Agents for Gold Trading with Technical Indicators and LLM-Filtered News Sentiment
dc.typeConference Paper

Files

Collections

Research