{"paper_id":"2401.03737","title":"Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection","authors":["Georgios Fatouros","Konstantinos Metaxas","John Soldatos","Dimosthenis Kyriazis"],"paper_date":"2024-01-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2401.03737v2","page_url":"https://thequant.space/flowcharts/can-large-language-models-beat-wall-street-unveiling-the-po/","scores":{"empirical_rigor":7.5,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes MarketSenseAI, an innovative GPT‑4‑based framework for stock selection that integrates chain‑of‑thought and in‑context learning to generate actionable, explainable investment signals.","quote":"This paper introduces MarketSenseAI, an innovative framework leveraging GPT-4’s advanced reasoning for selecting stocks in financial markets.","summary":"This paper introduces MarketSenseAI, an innovative framework leveraging GPT-4’s advanced reasoning for selecting stocks in financial markets. By integrating Chain of Thought and In-Context Learning, MarketSenseAI analyzes diverse data sources, including market trends, news, fundamentals, and…","strategy":"MarketSenseAI"},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs are assumed to be 5 basis points per trade.","type":"execution","stated":"explicit","quote":"Values in parenthesis represent the total returns after transaction costs (5bps/trade)."},{"assumption":"The investment universe is limited to the S&P 100 constituents.","type":"market","stated":"explicit","quote":"MarketSenseAI’s performance leverages stocks listed in the S&P 100 index, comprising the 100 largest and most established companies in U.S. equity markets."},{"assumption":"Equal‑weighted indices are used to counterbalance disparate stock performances.","type":"statistical","stated":"explicit","quote":"Our analysis places special emphasis on equal-weighted indices, which helps counterbalance this disparity and illustrates MarketSenseAI’s potential."},{"assumption":"GPT‑4 explanations improve signal accuracy, reliability and acceptance.","type":"model","stated":"explicit","quote":"A notable feature of this work is employing GPT-4 both as a predictive mechanism and signal evaluator, revealing the significant impact of the AI-generated explanations on signal accuracy, reliability and acceptance."}]},"datasets":{"status":"available","items":[{"name":"News articles","provider":null,"kind":"text-news","access":"unknown","period":"December 1, 2022 – February 29, 2024","universe":"S&P 100 stocks","quote":"A total of 163,483 articles published from December 1, 2022, to February 29, 2024, averaging 4.57 articles per day per stock"},{"name":"Fundamentals","provider":null,"kind":"fundamentals","access":"unknown","period":"starting from the second quarter of 2022","universe":"S&P 100 stocks","quote":"Financial data were gathered from 612 quarterly reports of the S&P 100 stocks, starting from the second quarter of 2022. This data set produced 608 unique fundamentals summaries, averaging about 6 per stock."},{"name":"Stock price data","provider":null,"kind":"market-prices","access":"unknown","period":"January 1, 2022 – February 29, 2024","universe":"S&P 100 stocks","quote":"Historical daily stock prices (adjusted close) from January 1, 2022, to February 29, 2024, were analyzed to compute stock price dynamics."},{"name":"Descriptions","provider":null,"kind":"other","access":"unknown","period":null,"universe":null,"quote":"Concise descriptions of each stock and its sector, employed by Algorithm 1 to identify similar stocks."}],"known":[],"sample":{"start":null,"end":null,"market":"S&P 100 stocks","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"5 basis points per trade are subtracted from reported returns.","quote":"Values in parenthesis represent the total returns after transaction costs (5bps/trade).","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"5 basis points per trade are subtracted from reported returns.","card_quote":"Values in parenthesis represent the total returns after transaction costs (5bps/trade).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The vanilla MarketSenseAI equally‑weighted strategy achieved a total return of 35.48% (32.94% after transaction costs) with a Sharpe ratio of 2.49 and a Sortino ratio of 3.87, outperforming the equally‑weighted S&P 100.","kind":"performance","quote":"The strategy following the complete set of MarketSenseAI’s signals (MS) equally weighted, yields an impressive total return of 35.48% (32.94% after transaction costs) with a Sharpe and Sortino ratio of 2.49 and 3.87, respectively."},{"finding":"Capitalization‑weighted MarketSenseAI portfolios delivered the highest risk‑adjusted scores, with MS‑L‑Cap achieving a total return of 66.22% (65.25% after costs) and a Sharpe ratio of 2.90.","kind":"performance","quote":"Values in parenthesis represent the total returns after transaction costs (5bps/trade)."},{"finding":"GPT‑4‑ranked top‑stock strategies (MS‑Top5‑GPT and MS‑Top10‑GPT) produced total returns of 50.96% (49.67% after costs) and 49.09% (48.07% after costs), respectively, markedly higher than naive trend‑following.","kind":"performance","quote":"The MS-Top5-GPT and MS-Top10-GPT strategies, which select the top 5 and top 10 GPT-4 ranked stocks respectively, achieved remarkable total returns of 50.96% (49.67% after costs) and 49.09% (48.07% after c…"},{"finding":"Across the 15‑month test on S&P 100 stocks, MarketSenseAI generated excess alpha between 10% and 30% and cumulative returns up to 72%, comparable risk profile to the broader market.","kind":"performance","quote":"Through empirical testing on the competitive S&P 100 stocks over a 15-month period, MarketSenseAI demonstrated exceptional performance, delivering excess alpha of 10% to 30% and achieving a cumulative return of up to 72% over the period, while maintaining a risk profile comparable to the broader market."}],"reported_performance":{"strategy":"MarketSenseAI","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":72,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"citations":{"cited_by_in_corpus":12,"by_independent_authors":12,"how_cited":{"used_as_baseline":0,"uses_method_or_data":3,"extends":0,"discusses_findings":0,"mentions":5,"unclassified":4},"independent_papers":[{"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/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","paper_date":"2024-07-26","authors":["Han Ding","Yinheng Li","Junhao Wang","Hang Chen","Doudou Guo","Yunbai Zhang"],"empirical_rigor":5.5,"page_url":"https://thequant.space/flowcharts/large-language-model-agent-in-financial-trading-a-survey/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2503.22693","title":"Bridging Language Models and Financial Analysis","paper_date":"2025-03-14","authors":["Alejandro Lopez-Lira","Jihoon Kwon","Sangwoon Yoon","Jy-yong Sohn","Chanyeol Choi"],"empirical_rigor":4,"page_url":"https://thequant.space/flowcharts/bridging-language-models-and-financial-analysis/"},"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":"2026-11-14T18:16:42Z"},"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/"}