{"paper_id":"2507.17211","title":"EFS: Evolutionary Factor Searching for Sparse Portfolio Optimization Using Large Language Models","authors":["Haochen Luo","Yuan Zhang","Chen Liu"],"paper_date":"2025-07-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2507.17211v1","page_url":"https://thequant.space/flowcharts/efs-evolutionary-factor-searching-for-sparse-portfolio-opti/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes Evolutionary Factor Search (EFS), a novel LLM‑guided framework that autonomously generates, evolves, and selects alpha factors for sparse portfolio optimization under ℓ0 constraints.","quote":"To address the limitations in current alpha mining algorithms and the challenges of sparse portfolio optimization, we propose Evolutionary Factor Search (EFS). EFS is a novel framework that leverages","summary":"Sparse portfolio optimization is a fundamental yet challenging problem in quantitative finance, since traditional approaches heavily relying on historical return statistics and static objectives can hardly adapt to dynamic market regimes. To address this issue, we propose Evolutionary Factor Search…","strategy":"EFS (Evolutionary Factor Search)"},"assumptions":{"status":"available","items":[{"assumption":"Portfolio selection is limited to a sparse set of assets (ℓ0 constraint).","type":"model","stated":"explicit","quote":"(LLMs) to autonomously generate, evolve, and select alpha factors under ℓ0 constraints."},{"assumption":"Only closing price and returns are used as input variables for factor construction.","type":"data","stated":"explicit","quote":"Considering implementation constraints and LLM context limits, we use only two variables—closing price and returns—for factor construction."},{"assumption":"Factor scores are normalized to the range [-1, 1] and the top‑5 scoring assets are selected at each step.","type":"execution","stated":"explicit","quote":"All factor scores are normalized to the range [-1, 1], and we select top-5 scoring assets at each step."},{"assumption":"Selected assets are equally weighted throughout the backtest.","type":"execution","stated":"explicit","quote":"To isolate factor quality, we apply equal weighting to selected assets throughout."}]},"datasets":{"status":"available","items":[{"name":"FF25","provider":"Kenneth R. French Data Library","kind":"benchmark","access":"public","period":null,"universe":null,"quote":"We first use five standard benchmark datasets from Kenneth R. French Data Library [Fama and French, 2023]: FF25, FF32, FF49, FF100 and FF100MEOP.","known_id":"french-library"},{"name":"FF32","provider":"Kenneth R. French Data Library","kind":"benchmark","access":"public","period":null,"universe":null,"quote":"We first use five standard benchmark datasets from Kenneth R. French Data Library [Fama and French, 2023]: FF25, FF32, FF49, FF100 and FF100MEOP.","known_id":"french-library"},{"name":"FF49","provider":"Kenneth R. French Data Library","kind":"benchmark","access":"public","period":null,"universe":null,"quote":"We first use five standard benchmark datasets from Kenneth R. French Data Library [Fama and French, 2023]: FF25, FF32, FF49, FF100 and FF100MEOP.","known_id":"french-library"},{"name":"FF100","provider":"Kenneth R. French Data Library","kind":"benchmark","access":"public","period":null,"universe":null,"quote":"We first use five standard benchmark datasets from Kenneth R. French Data Library [Fama and French, 2023]: FF25, FF32, FF49, FF100 and FF100MEOP.","known_id":"french-library"},{"name":"US50","provider":null,"kind":"market-prices","access":"public","period":"2019 to 2024","universe":"top 50 U.S. large‑cap stocks by market capitalization","quote":"US market (US50), comprises the top 50 U.S. large‑cap stocks by market capitalization, selected from the S&P 500 and NASDAQ indices, with data spanning from 2019 to 2024."},{"name":"HSI45","provider":null,"kind":"market-prices","access":"public","period":"2022 to 2025","universe":"top 45 companies from the Hang Seng Technology Index","quote":"Hong Kong market (HSI45), includes the top 45 companies from the Hang Seng Technology Index, based on market capitalization, from 2022 to 2025."}],"known":[],"sample":{"start":null,"end":null,"market":"US equities (US50, HSI45, CSI300)","asset_class":"equities","frequency":"daily"},"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":"EFS achieves the best performance across all five Fama‑French benchmark datasets under the standard sparse setting (m = 10), with only minor differences between GPT‑4.1 and DeepSeek back‑ends.","kind":"performance","quote":"Under the standard sparse setting (m = 10), our proposed EFS framework achieves the best performance across all asset pools, with only minor differences between the GPT-4.1 and DeepSeek backends."},{"finding":"On the US50 dataset, EFS‑GPT (CW = 39.67, SR = 0.154) and EFS‑DeepSeek (CW = 32.99, SR = 0.149) deliver a 7× improvement over the 1/N baseline.","kind":"performance","quote":"On US50, EFS-GPT (CW = 39.67, SR = 0.154) and EFS-DeepSeek (CW = 32.99, SR = 0.149) deliver 7× improvement over the 1/N baseline."}],"reported_performance":{"strategy":"EFS (Evolutionary Factor Search)","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"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":"2026-11-14T17:31:32Z"},"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/"}