{"paper_id":"2309.03079","title":"GPT-InvestAR: Enhancing Stock Investment Strategies through Annual Report Analysis with Large Language Models","authors":["Udit Gupta"],"paper_date":"2023-09-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.03079v1","page_url":"https://thequant.space/flowcharts/gpt-investar-enhancing-stock-investment-strategies-through/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes extracting features from annual 10‑K reports using a large language model and training a machine‑learning model on these LLM outputs combined with historical price data to select stocks.","quote":"The insights generated by the LLM are compiled in a Quant styled dataset and augmented by historical stock price data. A Machine Learning model is then trained with LLM outputs as features.","summary":"Annual Reports of publicly listed companies contain vital information about their financial health which can help assess the potential impact on Stock price of the firm. These reports are comprehensive in nature, going up to, and sometimes exceeding, 100 pages. Analysing these reports is cumbersome…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The study is limited to the top 1500 US companies by market cap that file 10‑K reports.","type":"market","stated":"explicit","quote":"The stocks considered for this paper are from the US stock universe. Specifically, the top 1500 companies by market cap in the US which are part of the S&P 500 largecap index, S&P 400 midcap index and S&P 600 smallcap index."},{"assumption":"Annual‑report‑based signals are assumed to have a longer investment horizon than short‑term news‑driven signals.","type":"execution","stated":"explicit","quote":"As these reports are published annually, the signals generated from these are of longer duration and stock selection using these signals…"},{"assumption":"Training data covers 2002‑2017 and testing data covers 2018‑2023.","type":"data","stated":"explicit","quote":"In this exercise, data from 2002 to 2017 is considered for training the ML model, and data from 2018 to 2023 is considered for testing."}]},"datasets":{"status":"available","items":[{"name":"Historical 10‑K filings","provider":"SEC","kind":"fundamentals","access":"public","period":"2002-2023","universe":"top 1500 US companies by market cap","quote":"To construct the dataset, access to historical 10-K filings of the top 1500 companies, ranked by market capitalization, is required."},{"name":"Historical stock price data","provider":null,"kind":"market-prices","access":"unknown","period":"2002-2023","universe":"individual stocks and S&P 500 index","quote":"The insights generated by the LLM are compiled in a Quant styled dataset and augmented by historical stock price data."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The ML model built on GPT‑3.5‑derived features yields higher returns than the S&P 500 over the test period.","kind":"performance","quote":"The analysis of predictions made on the test set reveals that the Machine Learning model constructed using GPT 3.5 features outperforms in selecting stocks, resulting in returns that surpass those of the S&P 500 Index."},{"finding":"Both the 12‑month‑target and max‑return models outperform the S&P 500 from 2018 to 2023, with the max‑return model showing substantially higher gains.","kind":"performance","quote":"Figure 3 depicts the investment performance of $1 from the start of 2018 to the start of 2023 for two differently constructed models. While both models outperform the S&P 500 returns during this period..."},{"finding":"The max‑returns strategy can quadruple a $1 investment over a five‑year horizon.","kind":"performance","quote":"Figure 4b shows the best case scenario where the Max Returns strategy is able to quadruple the $1 investment in 5 y…"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":10,"citations":{"cited_by_in_corpus":8,"by_independent_authors":8,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":3,"unclassified":4},"independent_papers":[{"paper":{"paper_id":"2508.09935","title":"Language of Persuasion and Misrepresentation in Business Communication: A Textual Detection Approach","paper_date":"2025-08-13","authors":["Sayem Hossen","Monalisa Moon Joti","Md. Golam Rashed"],"empirical_rigor":4,"page_url":"https://thequant.space/flowcharts/language-of-persuasion-and-misrepresentation-in-business-com/"},"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":"2026-11-14T18:22:30Z"},"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/"}