{"paper_id":"2411.08404","title":"Quantifying Qualitative Insights: Leveraging LLMs to Market Predict","authors":["Hoyoung Lee","Youngsoo Choi","Yuhee Kwon"],"paper_date":"2024-11-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.08404v1","page_url":"https://thequant.space/flowcharts/quantifying-qualitative-insights-leveraging-llms-to-market/","scores":{"empirical_rigor":6.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a method that scores textual key factors from securities‑firm reports and rescales these scores to quantitative values for market prediction.","quote":"a crafted prompt is designed to assign scores to the key factors, converting qualitative insights into quantitative results.","summary":"Recent advancements in Large Language Models (LLMs) have the potential to transform financial analytics by integrating numerical and textual data. However, challenges such as insufficient context when fusing multimodal information and the difficulty in measuring the utility of qualitative outputs…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The occurrence frequency follows a t‑distribution with thicker tails than a normal distribution.","type":"statistical","stated":"explicit","quote":"Under the assumption of a t-distribution with thicker tails than a normal distribution, the occurrence frequency was extended from 21 days to 100 days."}]},"datasets":{"status":"available","items":[{"name":"Daily reports from securities firms","provider":null,"kind":"text-news","access":"unknown","period":"June 1, 2023 to May 31, 2024","universe":null,"quote":"The data used in our experiments covers the period from June 1, 2023, to May 31, 2024, with daily-level collection and analysis."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"LLMs outperform the baseline time‑series models at Look‑Back (l=1), achieving higher accuracy and lower RMSE.","kind":"performance","quote":"LLMs outperform the baseline models at Look-Back (𝑙= 1), but from Look-Back (𝑙= 2) onward, the past data becomes too diluted, and the meaning of the prediction becomes unclear."},{"finding":"Overall, LLMs consistently outperformed traditional time‑series models in market forecasting.","kind":"predictive-accuracy","quote":"The experimental results further highlight that LLMs consistently outperformed traditional time series models, particularly in capturing nuanced market trends."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":21,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[],"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":"2026-11-14T17:53:55Z"},"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/"}