Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting

• URL: http://arxiv.org/abs/2603.09085v1
• Date: Tue, 10 Mar 2026 01:54:12 GMT
• Title: Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting
• Abstract summary: This study generates sentiment scores from English and Chinese news headlines and integrates them with base metal indices, exchange rates, inflation rates, and energy prices.<n>We evaluate the predictive performance and economic utility of these models through long-short simulations on the Shanghai Metal Exchange from 2007 to 2024.
• Score: 0.8921166277011348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News [21.498084305999992]
  Large Language Models (LLMs) are rapidly transitioning from static Natural Language Processing (NLP) tasks to acting as dynamic decision-making agents.<n>Direct live trading is irreproducible and prone to outcome bias by confounding luck with skill, whereas existing static benchmarks are often confined to entity-level stock picking and ignore broader market attention.<n>This work provides new insights into the alignment between general reasoning and financial decision-making, and all data, codes, and experiments are released to promote sustainable financial agent research.
  arXiv  Detail & Related papers  (2026-03-18T02:31:28Z)
• Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion [55.80546131166094]
  This paper introduces an approach that integrates Large Language Models (LLMs) with daily financial news for stock price prediction.<n>We encode news articles using a pre-trained LLM and implement three attention-based pooling techniques to filter news based on stock relevance.<n> Experimental results demonstrate a 7.11% reduction in Mean Absolute Error (MAE) compared to the baseline.
  arXiv  Detail & Related papers  (2026-03-08T09:05:10Z)
• PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction [47.70107097572211]
  We introduce PriceSeer, a benchmark specifically designed for large language models performing stock prediction tasks.<n>PriceSeer includes 110 U.S. stocks from 11 industrial sectors, with each containing 249 historical data points.<n>We evaluate six cutting-edge LLMs under different prediction horizons, demonstrating their potential in generating investment strategies.
  arXiv  Detail & Related papers  (2025-12-31T08:35:46Z)
• A Hybrid Model for Stock Market Forecasting: Integrating News Sentiment and Time Series Data with Graph Neural Networks [0.0]
  This paper investigates a multimodal approach that integrates companies' news articles with their historical stock data to improve prediction performance.<n>Experiments on the US equities and Bloomberg datasets show that the GNN outperforms the LSTM baseline.<n> headlines contain stronger predictive signals than full articles, suggesting that concise news summaries play an important role in short-term market reactions.
  arXiv  Detail & Related papers  (2025-12-09T13:05:54Z)
• Predicting Stock Price Movement with LLM-Enhanced Tweet Emotion Analysis [2.4401219403555814]
  Accurately predicting short-term stock price movement remains a challenging task due to the market's inherent volatility and sensitivity to investor sentiment.<n>This paper discusses a deep learning framework that integrates emotion features extracted from tweet data with historical stock price information to forecast significant price changes on the following day.
  arXiv  Detail & Related papers  (2025-10-04T02:31:44Z)
• Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents [69.58565132975504]
  Large language models (LLMs) have demonstrated remarkable capabilities in natural language tasks.<n>We present the Agent Trading Arena, a virtual zero-sum stock market in which LLM-based agents engage in competitive multi-agent trading.
  arXiv  Detail & Related papers  (2025-02-25T08:41:01Z)
• News-Driven Stock Price Forecasting in Indian Markets: A Comparative Study of Advanced Deep Learning Models [0.0]
  Recent advancements in artificial intelligence (AI) and natural language processing (NLP) have significantly enhanced stock price prediction capabilities. We leverage 30 years of historical data from national banks in India, sourced from the National Stock Exchange, to forecast stock prices. Our approach utilizes state-of-the-art deep learning models, including multivariate multi-step Long Short-Term Memory (LSTM), Facebook Prophet with LightGBM optimized through Optuna, and Seasonal Auto-Regressive Integrated Moving Average (SARIMA)
  arXiv  Detail & Related papers  (2024-10-14T15:30:06Z)
• Predicting Stock Prices with FinBERT-LSTM: Integrating News Sentiment Analysis [2.7921137693344384]
  We use deep learning networks, based on the history of stock prices and articles of financial, business, technical news that introduce market information to predict stock prices. We developed a pre-trained NLP model known as FinBERT, designed to discern the sentiments within financial texts. This model utilizes news categories related to the stock market structure hierarchy, namely market, industry, and stock related news categories, combined with the stock market's stock price situation in the previous week for prediction.
  arXiv  Detail & Related papers  (2024-07-23T03:26:07Z)
• Natural Language Processing and Multimodal Stock Price Prediction [0.8702432681310401]
  This paper utilizes stock percentage change as training data, in contrast to the traditional use of raw currency values. The choice of percentage change aims to provide models with context regarding the significance of price fluctuations. The study employs specialized BERT natural language processing models to predict stock price trends.
  arXiv  Detail & Related papers  (2024-01-03T01:21:30Z)
• Stock Movement and Volatility Prediction from Tweets, Macroeconomic Factors and Historical Prices [20.574163667057476]
  Prior research using tweet data for stock market prediction faces three challenges. ECON has an adept tweets filter that efficiently extracts and decodes the vast array of tweet data. It discerns multi-level relationships among stocks, sectors, and macroeconomic factors through a self-aware mechanism in semantic space.
  arXiv  Detail & Related papers  (2023-12-04T22:27:43Z)
• Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models [48.87381259980254]
  We document the capability of large language models (LLMs) like ChatGPT to predict stock market reactions from news headlines without direct financial training.<n>Using post-knowledge-cutoff headlines, GPT-4 captures initial market responses, achieving approximately 90% portfolio-day hit rates for the non-tradable initial reaction.
  arXiv  Detail & Related papers  (2023-04-15T19:22:37Z)
• Stock Price Prediction Under Anomalous Circumstances [81.37657557441649]
  This paper aims to capture the movement pattern of stock prices under anomalous circumstances. We train ARIMA and LSTM models at the single-stock level, industry level, and general market level. Based on 100 companies' stock prices in the period of 2016 to 2020, the models achieve an average prediction accuracy of 98%.
  arXiv  Detail & Related papers  (2021-09-14T18:50:38Z)
• A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data [20.392440676633573]
  This paper presents a framework that predicts price movement of cryptocurrencies from trade-by-trade data. The model is trained to achieve high performance on nearly a year of trade-by-trade data. In a realistic trading simulation setting, the prediction made by the model could be easily monetized.
  arXiv  Detail & Related papers  (2020-10-11T10:42:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.