Search papers, labs, and topics across Lattice.
This paper investigates the use of sentiment extracted from news headlines via finetuned LLMs to forecast aluminum prices on the Shanghai Metal Exchange. They finetuned the Qwen3 model on news headlines from Reuters, Dow Jones Newswires, and China News Service, generating monthly sentiment scores. Integrating this sentiment data with traditional tabular data in an LSTM model significantly improves forecasting performance, particularly during periods of high market volatility, achieving a Sharpe ratio of 1.04 compared to 0.23 for tabular data alone.
Finetuning LLMs on news sentiment boosts aluminum price forecasting, especially when markets are most turbulent.
By capturing the prevailing sentiment and market mood, textual data has become increasingly vital for forecasting commodity prices, particularly in metal markets. However, the effectiveness of lightweight, finetuned large language models (LLMs) in extracting predictive signals for aluminum prices, and the specific market conditions under which these signals are most informative, remains under-explored. This study generates monthly sentiment scores from English and Chinese news headlines (Reuters, Dow Jones Newswires, and China News Service) and integrates them with traditional tabular data, including base metal indices, exchange rates, inflation rates, and energy prices. We evaluate the predictive performance and economic utility of these models through long-short simulations on the Shanghai Metal Exchange from 2007 to 2024. Our results demonstrate that during periods of high volatility, Long Short-Term Memory (LSTM) models incorporating sentiment data from a finetuned Qwen3 model (Sharpe ratio 1.04) significantly outperform baseline models using tabular data alone (Sharpe ratio 0.23). Subsequent analysis elucidates the nuanced roles of news sources, topics, and event types in aluminum price forecasting.
