{"paper_id":"2510.26228","title":"ChatGPT in Systematic Investing -- Enhancing Risk-Adjusted Returns with LLMs","authors":["Nikolas Anic","Andrea Barbon","Ralf Seiz","Carlo Zarattini"],"paper_date":"2025-10-30","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.26228v1","page_url":"https://thequant.space/flowcharts/chatgpt-in-systematic-investing----enhancing-risk-adjusted-r/","scores":{"empirical_rigor":9,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes an LLM‑enhanced cross‑sectional momentum strategy that uses ChatGPT scores from firm‑specific news to condition stock selection and portfolio weights.","quote":"The LLM then evaluates whether recent news supports a continuation of past returns, producing a score that conditions both stock selection and portfolio weights.","summary":"This paper investigates whether large language models (LLMs) can improve cross-sectional momentum strategies by extracting predictive signals from firm-specific news. We combine daily U.S. equity returns for S&P 500 constituents with high-frequency news data and use prompt-engineered queries to…","strategy":"LLM-enhanced momentum strategy"},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs are assumed to be 2 basis points per trade.","type":"execution","stated":"explicit","quote":"These performance gains remain robust even after accounting for conservative estimates of transaction costs of 2 bps."},{"assumption":"Monthly rebalancing is used because it yields lower turnover and costs than weekly rebalancing.","type":"execution","stated":"explicit","quote":"We find that a monthly rebalancing frequency yields significantly better results than a weekly one."},{"assumption":"The baseline and LLM‑enhanced portfolios share the same universe and rebalancing frequency, isolating the effect of the LLM.","type":"market","stated":"explicit","quote":"Both strategies are described in Section 2. To ensure comparability, the baseline universe and the rebalancing frequency are the same for both portfolios."},{"assumption":"The LLM model and hyperparameters are selected solely on validation‑set performance to avoid overfitting.","type":"model","stated":"explicit","quote":"The LLM model, together with its hyperparameters, is selected based solely on Validation Set performance."},{"assumption":"Out‑of‑sample period starts after the model’s pre‑training cutoff, so results are not due to information leakage.","type":"data","stated":"explicit","quote":"Importantly, the out‑of‑sample period begins after the model’s pre‑training cut‑off, ensuring that the observed gains cannot be attributed to information leakage."}]},"datasets":{"status":"available","items":[{"name":"Finreon internal dataset","provider":"Finreon (internal)","kind":"market-prices","access":"proprietary","period":null,"universe":"U.S. equities (S&P 500 constituents)","quote":"First, we use an internal Finreon dataset, similar in structure and coverage to the CRSP database, which provides daily total returns and market capitalization data for U.S. equities."},{"name":"Stock News API","provider":"Stock News API","kind":"text-news","access":"commercial","period":null,"universe":"Firm‑level news for S&P 500 constituents","quote":"Second, we obtain high-frequency stock‑specific news from the Stock News API. This dataset includes publication timestamps with second‑level precision..."},{"name":"FRED risk‑free rate series","provider":"Federal Reserve Economic Data (FRED)","kind":"macro","access":"public","period":null,"universe":null,"quote":"Third, we retrieve the U.S. risk‑free rate from the Federal Reserve Economic Data (FRED) database.","known_id":"fred"}],"known":[{"id":"fred","name":"FRED","provider":"Federal Reserve Bank of St. Louis","kind":"macro","access":"public","quote":"Third, we retrieve the U.S. risk-free rate from the Federal Reserve Economic Data (FRED) database.","mentions":2,"used_in":1},{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"First, we use an internal Finreon dataset, similar in structure and coverage to the CRSP database, which provides daily total returns and market capitalization data for U.S. equities.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"S&P 500 stocks","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"2 basis points per trade (conservative estimate for highly liquid S&P 500 stocks)","quote":"All results are computed under the assumption of 2 basis points of transaction costs per trade, which is a conservative estimate given the high liquidity of S&P 500 stocks in our sample.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"2 basis points per trade (conservative estimate for highly liquid S&P 500 stocks)","card_quote":"All results are computed under the assumption of 2 basis points of transaction costs per trade, which is a conservative estimate given the high liquidity of S&P 500 stocks in our sample.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"In the full sample the LLM‑enhanced portfolio achieves a Sharpe ratio of 0.69 versus 0.57 for the baseline.","kind":"performance","quote":"In the full‑sample evaluation, the LLM‑enhanced portfolio exhibits a Sharpe ratio of 0.69, compared to 0.57 for the baseline."},{"finding":"Out‑of‑sample Sharpe improves to 1.06 from 0.79, and Sortino to 1.28 from 0.93, with returns rising from ~24% to 30%.","kind":"performance","quote":"... the Sharpe ratio improves from 0.79 for the baseline to 1.06 for the LLM‑enhanced strategy, while the Sortino ratio increases from 0.93 to 1.28. The total return increases from approximately 24% to 30%."},{"finding":"Volatility declines slightly (full sample 24% vs 26%; out‑of‑sample 22% vs 24%) and maximum drawdown improves (‑31% vs ‑33%).","kind":"performance","quote":"Volatility decreases slightly from 26% to 24%, while the maximum drawdown improves from −33% to −31%."},{"finding":"Turnover is higher for the LLM‑enhanced strategy but net returns remain superior after accounting for the 2 bps costs.","kind":"performance","quote":"all reported results are net of transaction costs, the increased turnover is offset by the stronger predictive signals."},{"finding":"A time‑series regression yields an annualized alpha of 3.26% for the LLM‑enhanced returns, significant only at the 10% level.","kind":"statistical","quote":"a time‑series regression of LLM‑enhanced returns on baseline returns yields a positive annualized alpha of 3.26%, but the estimate is statistically significant only at the 10% level."}],"reported_performance":{"strategy":"LLM-enhanced momentum strategy","sharpe":0.69,"sharpe_benchmark":0.57,"annual_return_pct":18,"total_return_pct":null,"max_drawdown_pct":31},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":56,"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":"2026-11-14T16:39:08Z"},"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/"}