{"paper_id":"2502.00029","title":"AlphaSharpe: LLM-Driven Discovery of Robust Risk-Adjusted Metrics","authors":["Kamer Ali Yuksel","Hassan Sawaf"],"paper_date":"2025-01-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.00029v2","page_url":"https://thequant.space/flowcharts/alphasharpe-llm-driven-discovery-of-robust-risk-adjusted-me/","scores":{"empirical_rigor":6,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes AlphaSharpe, a novel framework that uses large language models to iteratively evolve and optimize financial risk‑adjusted metrics.","quote":"this paper introduces AlphaSharpe, a novel framework leveraging large language models (LLMs) to iteratively evolve and optimize financial metrics to discover enhanced risk‑return metrics that outperform traditional approaches","summary":"Financial metrics like the Sharpe ratio are pivotal in evaluating investment performance by balancing risk and return. However, traditional metrics often struggle with robustness and generalization, particularly in dynamic and volatile market conditions. This paper introduces AlphaSharpe, a novel…","strategy":"AlphaSharpe"},"assumptions":{"status":"available","items":[{"assumption":"Metrics are evaluated on historical log‑return data and assumed to generalize to future Sharpe ratios.","type":"data","stated":"explicit","quote":"Apply the proposed metric to a historical asset log‑return dataset to compute scores."},{"assumption":"Future Sharpe ratios are available for out‑of‑sample evaluation.","type":"data","stated":"implied","quote":"Evaluate the alignment of scores with future Sharpe ratios via: • Spearman’s Rho"},{"assumption":"The dataset of 3,246 US stocks and ETFs is representative of the market.","type":"market","stated":"implied","quote":"The dataset, comprising 15 years of historical data from 3,246 US stocks and ETFs"}]},"datasets":{"status":"available","items":[{"name":"Historical US stock and ETF dataset","provider":null,"kind":"market-prices","access":"unknown","period":"15 years","universe":"3,246 US stocks and ETFs","quote":"The dataset, comprising 15 years of historical data from 3,246 US stocks and ETFs, was split into overlapping folds"}],"known":[],"sample":{"start":null,"end":null,"market":"US stocks and ETFs","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"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":"AlphaSharpe metrics achieve over 3× higher Spearman and Kendall correlations than traditional metrics.","kind":"predictive-accuracy","quote":"AlphaSharpe achieved over 3x higher Spearman and Kendall correlations than traditional metrics"},{"finding":"Metric αS4 attains a Spearman correlation of 0.409, more than three times the Sharpe Ratio’s 0.130.","kind":"statistical","quote":"αS4 achieves a correlation of 0.409, which is over 3x higher than the Sharpe Ratio"},{"finding":"αS2 improves NDCG@25% to 0.636, a +62% increase over the Sharpe Ratio.","kind":"statistical","quote":"αS2 delivers a substantial improvement, achieving a score of 0.636, reflecting a +62% increase over the Sharpe Ratio"},{"finding":"Portfolios built with αS metrics show a +89.11% Sharpe improvement over the Sharpe Ratio and +95.73% over PSR.","kind":"performance","quote":"AlphaSharpe achieved a +89.11% improvement over the Sharpe Ratio and a +95.73% improvement over PSR"},{"finding":"The framework demonstrates 3× predictive power for future risk‑returns and 2× portfolio performance.","kind":"predictive-accuracy","quote":"an empirical demonstration of 3x predictive power for future risk‑returns, and 2x portfolio performance"}],"reported_performance":{"strategy":"AlphaSharpe","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":65,"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":"2026-11-14T17:46:36Z"},"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/"}