{"paper_id":"2512.24526","title":"Generative AI-enhanced Sector-based Investment Portfolio Construction","authors":["Alina Voronina","Oleksandr Romanko","Ruiwen Cao","Roy H. Kwon","Rafael Mendoza-Arriaga"],"paper_date":"2025-12-31","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2512.24526v1","page_url":"https://thequant.space/flowcharts/generative-ai-enhanced-sector-based-investment-portfolio-con/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper evaluates applying large language models to quantitative sector‑based portfolio construction and combines their stock selection with classical mean‑variance optimization.","quote":"This study set out to evaluate how effectively large language models (LLMs) from leading AI providers (OpenAI, Google, Anthropic, DeepSeek, and xAI) can be applied to the task of quantitative sector-based portfolio construction.","summary":"This paper investigates how Large Language Models (LLMs) from leading providers (OpenAI, Google, Anthropic, DeepSeek, and xAI) can be applied to quantitative sector-based portfolio construction. We use LLMs to identify investable universes of stocks within S&P 500 sector indices and evaluate how…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"LLMs have training cut‑off dates before 2025, so analysis is split into in‑sample and out‑of‑sample periods.","type":"model","stated":"explicit","quote":"Because most of the large language models (LLMs) used in this study have training cut‑off dates before 2025, we divided the analysis into one in‑sample period and two out‑of‑sample periods"},{"assumption":"Each LLM is prompted to select and weight exactly 20 stocks per sector.","type":"execution","stated":"explicit","quote":"Each model was prompted to select and weight 20 stocks per sector"},{"assumption":"Portfolio evaluation uses a mean‑variance optimization framework.","type":"statistical","stated":"explicit","quote":"The resulting portfolios were then evaluated using the mean–variance optimization framework to compare LLM‑generated results with those produced through traditional quantitative methods"},{"assumption":"Adjusted closing prices from Yahoo Finance are used for returns and risk calculations.","type":"data","stated":"explicit","quote":"Market data were obtained primarily from Yahoo Finance, which provided adjusted closing prices for both individual company stocks and the S&P 500 sector indices"},{"assumption":"Risk‑free rate is set to 2% for Sharpe ratio calculations.","type":"statistical","stated":"explicit","quote":"The risk‑free rate is set to 2% (0.02) as per standards"},{"assumption":"Sector constituents are validated against Wikipedia and TradingView listings.","type":"data","stated":"explicit","quote":"list from Wikipedia [12] was used to identify which companies belong to each sector according to the GICS classification. • For an additional layer of validation, the resulting lists were compared with the sector compositions available on TradingView [13]"}]},"datasets":{"status":"available","items":[{"name":"Yahoo Finance adjusted closing prices","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"five years preceding Jan 2025 and Jan‑Ju","universe":"S&P 500 sector constituents and sector indices","quote":"Market data were obtained primarily from Yahoo Finance, which provided adjusted closing prices for both individual company stocks and the S&P 500 sector indices","known_id":"yahoo-finance"},{"name":"Wikipedia GICS sector list","provider":"Wikipedia","kind":"benchmark","access":"public","period":null,"universe":"S&P 500 sector constituents","quote":"list from Wikipedia [12] was used to identify which companies belong to each sector according to the GICS classification"},{"name":"TradingView sector composition","provider":"TradingView","kind":"benchmark","access":"public","period":null,"universe":"S&P 500 sector constituents","quote":"For an additional layer of validation, the resulting lists were compared with the sector compositions available on TradingView [13]"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"7 Market data were obtained primarily from Yahoo Finance, which provided adjusted closing prices for both individual company stocks and the S&P 500 sector indices.","mentions":3,"used_in":2}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"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":"During the stable market period (Jan‑Mar 2025), LLM‑weighted portfolios frequently outperformed sector indices on cumulative return and Sharpe ratio.","kind":"performance","quote":"During stable market conditions, LLM‑weighted portfolios frequently outperformed sector indices on both cumulative return and risk‑adjusted (Sharpe ratio) measures"},{"finding":"In the volatile period (Apr‑Jun 2025), many LLM portfolios underperformed their sector benchmarks.","kind":"negative","quote":"during the volatile period, many LLM portfolios underperformed"},{"finding":"Combining LLM‑based stock selection with traditional mean‑variance optimization improves both performance and consistency of the portfolios.","kind":"performance","quote":"Importantly, when LLM‑based stock selection is combined with traditional optimization techniques, portfolio outcomes improve in both performance and consistency"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":29,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"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":"2026-11-14T17:17:33Z"},"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/"}