{"paper_id":"2308.06260","title":"ChatGPT-based Investment Portfolio Selection","authors":["Oleksandr Romanko","Akhilesh Narayan","Roy H. Kwon"],"paper_date":"2023-08-11","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2308.06260v1","page_url":"https://thequant.space/flowcharts/chatgpt-based-investment-portfolio-selection/","scores":{"empirical_rigor":6,"math_complexity":5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using ChatGPT to generate a stock universe from the S&P 500 and then applying traditional portfolio optimization to those stocks, creating a hybrid approach for investment selection.","quote":"... when stocks selection by ChatGPT is combined with established portfolio optimization models, we achieve even better results.","summary":"In this paper, we explore potential uses of generative AI models, such as ChatGPT, for investment portfolio selection. Trusting investment advice from Generative Pre-Trained Transformer (GPT) models is a challenge due to model “hallucinations”, necessitating careful verification and validation of…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"GPT‑4 was trained on data prior to September 2021, so in‑sample parameters are computed using historical data before that date.","type":"data","stated":"explicit","quote":"At the time of writing, the GPT‑4 model was trained on data prior to September 2021. Consequently, we used historical data up prior to September 2021 as our in‑sample data for portfolio selection models"},{"assumption":"The stock universe is limited to constituents of the S&P 500, specifically the 485 stocks for which complete price histories are available.","type":"market","stated":"explicit","quote":"From all stocks included in the S&P500 market index, we obtained complete historical timeseries (both in‑sample and out‑of‑sample) for 485 stocks using Yahoo Finance."},{"assumption":"ChatGPT’s recommendations reflect the frequency and positivity of mentions in its training text, implying a sentiment‑based selection bias.","type":"model","stated":"implied","quote":"The underlying hypothesis is that the frequency and positivity of mentions related to a given stock in its training data"},{"assumption":"Portfolios are re‑balanced only at the start of each out‑of‑sample testing period, with no intra‑period trading.","type":"execution","stated":"implied","quote":"Out‑of‑sample data used for testing and comparing portfolios span three distinct periods:"}]},"datasets":{"status":"available","items":[{"name":"Historical price series for S&P 500 constituents","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":null,"universe":"485 S&P 500 stocks","quote":"From all stocks included in the S&P500 market index, we obtained complete historical timeseries (both in‑sample and out‑of‑sample) for 485 stocks using Yahoo Finance.","known_id":"yahoo-finance"},{"name":"GPT‑4 model via API","provider":"OpenAI","kind":"text-news","access":"commercial","period":null,"universe":null,"quote":"In this study, we utilized the GPT‑4 model through its API."}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"From all stocks included in the S&P500 market index, we obtained complete historical timeseries (both in-sample and out-of-sample) for 485 stocks using Yahoo Finance.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"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":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Portfolios built from ChatGPT‑selected stock universes outperform those derived from cardinality‑constrained optimizations, showing ChatGPT excels at stock pre‑selection.","kind":"performance","quote":"the portfolios constructed from the ChatGPT trading universes outperform those derived from cardinality‑constrained optimizations, implying that ChatGPT is good at stock pre‑selection."},{"finding":"Combining ChatGPT‑selected stocks with traditional portfolio optimization yields better risk‑reward profiles than using either approach alone.","kind":"performance","quote":"when stocks selection by ChatGPT is combined with established portfolio optimization models, we achieve even better results."},{"finding":"ChatGPT alone is less effective at assigning optimal weights to stocks within a portfolio.","kind":"negative","quote":"ChatGPT is effective in stock selection but may not perform as well in assigning optimal weights to stocks within the portfolio."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":15,"citations":{"cited_by_in_corpus":5,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":3},"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":"2026-11-14T18:23:33Z"},"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/"}