{"id":"https://openalex.org/W4416303649","doi":"https://doi.org/10.1631/fitee.2500386","title":"A survey on large language model-based alpha mining","display_name":"A survey on large language model-based alpha mining","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4416303649","doi":"https://doi.org/10.1631/fitee.2500386"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2500386","is_oa":true,"landing_page_url":"https://doi.org/10.1631/fitee.2500386","pdf_url":"https://link.springer.com/content/pdf/10.1631/FITEE.2500386.pdf","source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology &amp; Electronic Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1631/FITEE.2500386.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035077992","display_name":"Junjie Zhang","orcid":"https://orcid.org/0000-0001-7962-0680"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Junjie Zhang","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7962-0680","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018892437","display_name":"Shuoling Liu","orcid":"https://orcid.org/0009-0003-1960-3004"},"institutions":[{"id":"https://openalex.org/I4210107834","display_name":"Development Fund","ror":"https://ror.org/01rkhv978","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I4210107834"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Shuoling Liu","raw_affiliation_strings":["E Fund Management Co., Ltd., Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"E Fund Management Co., Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210107834"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tongzhe Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107834","display_name":"Development Fund","ror":"https://ror.org/01rkhv978","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I4210107834"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Tongzhe Zhang","raw_affiliation_strings":["E Fund Management Co., Ltd., Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"E Fund Management Co., Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210107834"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101935762","display_name":"Yuchen Shi","orcid":"https://orcid.org/0000-0002-1885-8043"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210107834","display_name":"Development Fund","ror":"https://ror.org/01rkhv978","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I4210107834"]}],"countries":["NO","SG"],"is_corresponding":false,"raw_author_name":"Yuchen Shi","raw_affiliation_strings":["Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore, Singapore","E Fund Management Co., Ltd., Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1885-8043","affiliations":[{"raw_affiliation_string":"Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"E Fund Management Co., Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210107834"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035077992"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17980419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"10","first_page":"1809","last_page":"1821"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20389999449253082,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20389999449253082,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.062199998646974564,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.04619999974966049,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5536999702453613},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/alpha","display_name":"Alpha (finance)","score":0.42570000886917114},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.36980000138282776},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3167000114917755},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668999791145325},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5683000087738037},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C64943373","wikidata":"https://www.wikidata.org/wiki/Q2651003","display_name":"Alpha (finance)","level":4,"score":0.42570000886917114},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2809999883174896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2500386","is_oa":true,"landing_page_url":"https://doi.org/10.1631/fitee.2500386","pdf_url":"https://link.springer.com/content/pdf/10.1631/FITEE.2500386.pdf","source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology &amp; Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1631/fitee.2500386","is_oa":true,"landing_page_url":"https://doi.org/10.1631/fitee.2500386","pdf_url":"https://link.springer.com/content/pdf/10.1631/FITEE.2500386.pdf","source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology &amp; Electronic Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416303649.pdf","grobid_xml":"https://content.openalex.org/works/W4416303649.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1995834279","https://openalex.org/W2122298188","https://openalex.org/W2125520394","https://openalex.org/W3010604601","https://openalex.org/W3021711601","https://openalex.org/W3124798136","https://openalex.org/W4205539948","https://openalex.org/W4211170237","https://openalex.org/W4224220755","https://openalex.org/W4249545506","https://openalex.org/W4312091386","https://openalex.org/W4327810158","https://openalex.org/W4381795742","https://openalex.org/W4385507512","https://openalex.org/W4391631759","https://openalex.org/W4391912539","https://openalex.org/W4392460414","https://openalex.org/W4392679398","https://openalex.org/W4396626886","https://openalex.org/W4399836596","https://openalex.org/W4402426816","https://openalex.org/W4402683967","https://openalex.org/W4402683984","https://openalex.org/W4402963437","https://openalex.org/W4403623282","https://openalex.org/W4404306500","https://openalex.org/W4404350209","https://openalex.org/W4405828000","https://openalex.org/W4406779522","https://openalex.org/W4409364798","https://openalex.org/W4414430270","https://openalex.org/W4414786520","https://openalex.org/W4414844637","https://openalex.org/W4415062592","https://openalex.org/W4415235511","https://openalex.org/W6929387458","https://openalex.org/W6947816561"],"related_works":[],"abstract_inverted_index":{"Alpha":[0],"mining,":[1],"which":[2,38],"refers":[3],"to":[4,87,130,197],"the":[5,77,199],"systematic":[6],"discovery":[7],"of":[8,12,65,80,104,201],"data-driven":[9],"signals":[10],"predictive":[11],"future":[13,123,200],"cross-sectional":[14],"returns,":[15],"is":[16,150,186],"a":[17,40,62,151,187],"central":[18],"task":[19],"in":[20,25,33],"quantitative":[21,143,202],"research.":[22,203],"Recent":[23],"progress":[24],"large":[26],"language":[27],"models":[28],"(LLMs)":[29],"has":[30],"sparked":[31],"interest":[32],"LLM-based":[34,67],"alpha":[35,49,68],"mining":[36,50,69],"frameworks,":[37],"offer":[39],"promising":[41],"middle":[42],"ground":[43],"between":[44],"human-guided":[45],"and":[46,52,56,75,85,106,114,117,137,159,174,181,193],"fully":[47],"automated":[48],"approaches":[51],"deliver":[53],"both":[54,156],"speed":[55],"semantic":[57,182],"depth.":[58],"This":[59],"study":[60],"presents":[61],"structured":[63],"review":[64],"emerging":[66],"systems":[70],"from":[71,83],"an":[72],"agentic":[73],"perspective,":[74],"analyzes":[76],"functional":[78],"roles":[79],"LLMs,":[81],"ranging":[82],"miners":[84],"evaluators":[86],"interactive":[88],"assistants.":[89],"Despite":[90],"early":[91],"progress,":[92],"key":[93],"challenges":[94],"remain,":[95],"including":[96,125],"simplified":[97],"performance":[98],"evaluation,":[99],"limited":[100],"numerical":[101],"understanding,":[102],"lack":[103],"diversity":[105],"originality,":[107],"weak":[108],"exploration":[109],"dynamics,":[110],"temporal":[111],"data":[112,132],"leakage,":[113],"black-box":[115],"risks":[116],"compliance":[118],"challenges.":[119],"Accordingly,":[120],"we":[121],"outline":[122],"directions,":[124],"improving":[126],"reasoning":[127,195],"alignment,":[128],"expanding":[129],"new":[131],"modalities,":[133],"rethinking":[134],"evaluation":[135],"protocols,":[136],"integrating":[138],"LLMs":[139],"into":[140,171],"more":[141],"general-purpose":[142],"systems.":[144],"Our":[145],"analysis":[146],"suggests":[147],"that":[148],"LLM":[149],"scalable":[152],"interface":[153],"for":[154,178],"amplifying":[155],"domain":[157,165],"expertise":[158,166],"algorithmic":[160,176],"rigor,":[161],"as":[162],"it":[163],"amplifies":[164],"by":[167],"transforming":[168],"qualitative":[169],"hypotheses":[170],"testable":[172],"factors":[173],"enhances":[175],"rigor":[177],"rapid":[179],"backtesting":[180],"reasoning.":[183],"The":[184],"result":[185],"complementary":[188],"paradigm,":[189],"where":[190],"intuition,":[191],"automation,":[192],"language-based":[194],"converge":[196],"redefine":[198]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-11-17T00:00:00"}
