{"paper_id":"2411.00856","title":"AI in Investment Analysis: LLMs for Equity Stock Ratings","authors":["Kassiani Papasotiriou","Srijan Sood","Shayleen Reynolds","Tucker Balch"],"paper_date":"2024-10-30","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.00856v1","page_url":"https://thequant.space/flowcharts/ai-in-investment-analysis-llms-for-equity-stock-ratings/","scores":{"empirical_rigor":8,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes using a Large Language Model to predict equity stock ratings, presenting a reproducible framework that leverages multimodal financial data.","quote":"We demonstrate the novel use of an LLM for predicting stock ratings, addressing a significantly under-researched area.","summary":"Investment Analysis is a cornerstone of the Financial Services industry. The rapid integration of advanced machine learning techniques, particularly Large Language Models (LLMs), offers opportunities to enhance the equity rating process. This paper explores the application of LLMs to generate…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The GPT-4-32k model is assumed to have no information leakage because its training cutoff is set to September 2021.","type":"model","stated":"explicit","quote":"We utilize GPT-4-32k (v0613), hosted on Azure, which features a context window of 32,000 tokens and is trained on data up to"},{"assumption":"Evaluation of rating quality is based on forward returns quantiles, assuming that forward returns are a valid proxy for rating correctness.","type":"statistical","stated":"implied","quote":"Our results show that our benchmark method outperforms traditional stock rating methods when assessed by forward returns."},{"assumption":"The method does not fine‑tune the LLM, assuming that zero‑shot prompting is sufficient for cost‑effective performance.","type":"model","stated":"explicit","quote":"Since we do not fine-tune the model, the process remains cost-effective."}]},"datasets":{"status":"available","items":[{"name":"Fundamental financial data","provider":"SEC via finagg API","kind":"fundamentals","access":"public","period":"January 2022 to March 2024","universe":"S&P 500 constituents","quote":"We aggregate quarterly company fundamentals from 10‑Q and 10‑K filings from January 2022 to March 2024 using finagg API"},{"name":"Market price data","provider":null,"kind":"market-prices","access":"unknown","period":"January 2022 to June 2024","universe":"S&P 500 constituents","quote":"Our analysis focuses on US equities, specifically the 500 constituents of the S&P 500 index, using data spanning from January 2022 to the end of June 2024."},{"name":"Financial news articles","provider":null,"kind":"text-news","access":"unknown","period":"January 2022 to June 2024","universe":"S&P 500 constituents","quote":"on average per month, there are 39.63 articles, 187K characters, and 40K tokens."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"not_extracted","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"none","rule":"R0","candidates":{"front_matter":"unclear","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the classifier was not confident"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"The vanilla LLM model achieves a lower market‑relative MAE (1.447) than analyst ratings (1.570), indicating better predictive performance.","kind":"performance","quote":"Vanilla method has a lower MAE of 1.447 compared to the Analyst predictions, which has a Return MAE of 1.570."},{"finding":"Adding sentiment scores to fundamentals further improves MAE slightly (1.417) compared to fundamentals alone.","kind":"predictive-accuracy","quote":"Fundamentals + Sentiment 1.417 ± 0.747"},{"finding":"Using news summaries versus sentiment scores provides only a very small performance difference when fundamentals are not included.","kind":"performance","quote":"The performance difference between adding news as text versus news sentiment to the LLM is very small when other data is not included (i.e. Fundamentals)."},{"finding":"LLMs perform better for short‑term horizons, while traditional analysts perform better over longer horizons.","kind":"performance","quote":"News summaries are more beneficial for short-term predictions, while traditional analysts perform better over longer horizons."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2505.07078","title":"Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?","paper_date":"2025-05-11","authors":["Weixian Waylon Li","Hyeonjun Kim","Mihai Cucuringu","Tiejun Ma"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/can-llm-based-financial-investing-strategies-outperform-the/"},"question":"Do LLM‑based investment methods retain their advantage over longer investment horizons?","this_paper_finding":"LLMs perform better for short‑term horizons, while traditional analysts perform better over longer horizons.","other_paper_finding":"LLM timing‑based strategies lose their reported advantage when evaluated over longer horizons and a broader cross‑section of assets.","other_paper_quote":"Systematic backtests over two decades and 100+ symbols reveal that previously reported LLM advantages deteriorate significantly under broader cross-section and over a longer-term evaluation.","note":"Both findings show the LLM advantage vanishes for longer horizons: A finds LLMs beat analysts only short‑term, while B reports timing‑based LLM strategies lose their edge over longer periods and a broader asset cross‑sec","confidence":0.726}],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":3,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":1},"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":"2026-11-14T17:56:40Z"},"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/"}