{"paper_id":"2310.05627","title":"Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction","authors":["Yujie Ding","Shuai Jia","Tianyi Ma","Bingcheng Mao","Xiuze Zhou","Liuliu Li","Dongming Han"],"paper_date":"2023-10-09","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2310.05627v1","page_url":"https://thequant.space/flowcharts/integrating-stock-features-and-global-information-via-large/","scores":{"empirical_rigor":5,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a Self-Correlated Reinforcement Learning with Local-Global model (SCRL-LG) that aligns LLM news embeddings with stock features to improve stock return prediction.","quote":"To demonstrate the effectiveness of LLMs in predicting stock returns, we have introduced a novel approach known as Self-Correlated Reinforcement Learning with Local-Global model (SCRL-LG).","summary":"The remarkable achievements and rapid advancements of Large Language Models (LLMs) such as ChatGPT and GPT-4 have showcased their immense potential in quantitative investment. Traders can effectively leverage these LLMs to analyze financial news and predict stock returns accurately. However…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"All trades are executed at the closing price with a flat transaction cost of 0.3% and no slippage.","type":"execution","stated":"explicit","quote":"All transactions were executed at the closing prices, with a transaction cost of 0.3%."},{"assumption":"News used for alignment are selected from the previous 60 trading days.","type":"data","stated":"explicit","quote":"Finally, we select the news related to the selected stock features from the previous 60 trading days in the news corpus."},{"assumption":"The LLM embeddings can be aligned with stock feature space via KL divergence and PPO reinforcement learning.","type":"model","stated":"implied","quote":"We propose a Self-Correlated Reinforcement Learning (SCRL) framework, incorporating the Proximal Policy Optimization (PPO) paradigm"},{"assumption":"The market universe is limited to China A‑share stocks that were not suspended and listed before 2020.","type":"data","stated":"explicit","quote":"We exclude suspended stocks or the stocks listed after 2020."},{"assumption":"Predicted returns are sorted daily into ten quantiles and the top 10% is bought while others are liquidated.","type":"execution","stated":"explicit","quote":"Our strategy involved purchasing an equal allocation of stocks from the top 10% quantile while liquidating portfolios not belonging to this quantile."},{"assumption":"The LLM (Llama 7B) fine‑tuned on Chinese corpora provides meaningful representations for news headlines.","type":"model","stated":"explicit","quote":"... continued training Llama for an additional 2 epochs on 15 GB of Chinese corpus"}]},"datasets":{"status":"available","items":[{"name":"China A‑share dataset","provider":null,"kind":"market-prices","access":"unknown","period":"01/01/2019 to 12/31/2022","universe":"3506 stocks","quote":"The experiments are conducted on the China A‑shares market using a dataset comprising 3506 stocks and 342 daily features constructed from stock price‑volume data ranging from 01/01/2019 to 12/31/2022."},{"name":"News headlines corpus","provider":null,"kind":"text-news","access":"unknown","period":"01/01/2019 to 12/31/2022","universe":null,"quote":"Additionally, we collect news headlines during the same period, resulting in a dataset size of 162,845 headlines and 2,526,174 stock data points for training (from 01/01/2019 to 12/31/2021) and 849,173 data points for testing."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A flat transaction cost of 0.3% per trade is applied to all transactions.","quote":"All transactions were executed at the closing prices, with a transaction cost of 0.3%.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat transaction cost of 0.3% per trade is applied to all transactions.","card_quote":"All transactions were executed at the closing prices, with a transaction cost of 0.3%.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"SCRL‑LG outperforms all baselines, achieving higher Rank IC, annual return, Sharpe ratio, and lower max draw‑down compared to LG‑STOCK and LG‑LLM.","kind":"performance","quote":"The results show that SCRL‑LG yields noticeable improvements in all metrics compared to the methods above for generating global information."},{"finding":"SCRL‑LG shows increasing performance with longer prediction horizons, contrary to the Local model which degrades.","kind":"performance","quote":"Surprisingly, the SCRL‑LG model even exhibits performance improvements with increasing prediction horizons, accompanied by a decrease in turnover rate."},{"finding":"Incorporating global information (LG‑STOCK, LG‑LLM) mitigates the decline in predictive performance observed in the Local model.","kind":"predictive-accuracy","quote":"These results collectively indicate that the three proposed approaches for incorporating global information can effectively mitigate the decline in predictive performance observed in the Local model."},{"finding":"The proposed framework demonstrates superior Rank Information Coefficient and returns compared to models relying only on stock features in the China A‑share market.","kind":"performance","quote":"By implementing our framework, we have demonstrated superior performance in Rank Information Coefficient and returns, particularly compared to models relying only on stock features in the China A‑share market."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":51,"citations":{"cited_by_in_corpus":9,"by_independent_authors":8,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":6,"unclassified":2},"independent_papers":[{"paper":{"paper_id":"2412.20138","title":"TradingAgents: Multi-Agents LLM Financial Trading Framework","paper_date":"2024-12-28","authors":["Yijia Xiao","Edward Sun","Di Luo","Wei Wang"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/tradingagents-multi-agents-llm-financial-trading-framework/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:21:05Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}