{"id":"https://openalex.org/W4416198711","doi":"https://doi.org/10.1145/3768292.3770377","title":"FactorMAD: A Multi-Agent Debate Framework Based on Large Language Models for Interpretable Stock Alpha Factor Mining","display_name":"FactorMAD: A Multi-Agent Debate Framework Based on Large Language Models for Interpretable Stock Alpha Factor Mining","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416198711","doi":"https://doi.org/10.1145/3768292.3770377"},"language":null,"primary_location":{"id":"doi:10.1145/3768292.3770377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768292.3770377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037926433","display_name":"Yongkang Duan","orcid":"https://orcid.org/0000-0002-8610-2280"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitong Duan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8610-2280","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035555392","display_name":"C. Zhang","orcid":"https://orcid.org/0000-0002-6276-7958"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"chuheng zhang","raw_affiliation_strings":["microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6276-7958","affiliations":[{"raw_affiliation_string":"microsoft, Beijing, China","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101938872","display_name":"Jian Li","orcid":"https://orcid.org/0000-0003-4650-3925"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4650-3925","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9067028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"605","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.8628000020980835,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.8628000020980835,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.02070000022649765,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.01600000075995922,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8367999792098999},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5611000061035156},{"id":"https://openalex.org/keywords/stock-market","display_name":"Stock market","score":0.484499990940094},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4595000147819519},{"id":"https://openalex.org/keywords/stock","display_name":"Stock (firearms)","score":0.41429999470710754},{"id":"https://openalex.org/keywords/factor-analysis","display_name":"Factor analysis","score":0.39800000190734863},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3953999876976013}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8367999792098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6305999755859375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5759999752044678},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C2780299701","wikidata":"https://www.wikidata.org/wiki/Q475000","display_name":"Stock market","level":3,"score":0.484499990940094},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C204036174","wikidata":"https://www.wikidata.org/wiki/Q909380","display_name":"Stock (firearms)","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C10879293","wikidata":"https://www.wikidata.org/wiki/Q726474","display_name":"Factor analysis","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C19244329","wikidata":"https://www.wikidata.org/wiki/Q208697","display_name":"Financial market","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.3084999918937683},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3768292.3770377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768292.3770377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2136120210","https://openalex.org/W2143139512","https://openalex.org/W2166215547","https://openalex.org/W2938815980","https://openalex.org/W3171817614","https://openalex.org/W4283804236","https://openalex.org/W4285333868","https://openalex.org/W4381795742","https://openalex.org/W4389519889","https://openalex.org/W4391631536","https://openalex.org/W4393967771","https://openalex.org/W4400277517","https://openalex.org/W4402672029","https://openalex.org/W4402683984","https://openalex.org/W4403367728","https://openalex.org/W4404351480","https://openalex.org/W4406800520","https://openalex.org/W4409346853","https://openalex.org/W4409364798","https://openalex.org/W4410636467","https://openalex.org/W4415798198"],"related_works":[],"abstract_inverted_index":{"In":[0,74],"quantitative":[1],"investment,":[2],"alpha":[3,92,190],"factor":[4,32,45,93,120,128,138,165],"mining":[5,166,188],"plays":[6],"a":[7,41,54,80,126,184],"crucial":[8],"role":[9],"in":[10,168,192],"predicting":[11],"stock":[12,155],"returns.":[13],"Traditional":[14],"approaches":[15,50],"rely":[16],"on":[17,24,85,153],"human":[18],"experts":[19],"to":[20,68,134,144],"design":[21],"factors":[22,108,191],"based":[23,84],"financial":[25,193],"intuition.":[26],"To":[27,118],"enhance":[28,119],"the":[29,177],"efficiency":[30],"of":[31,56,141,179],"mining,":[33],"recent":[34],"machine":[35],"learning":[36],"(ML)":[37],"methods":[38,167],"have":[39],"driven":[40],"shift":[42],"toward":[43],"automated":[44,164],"mining.":[46,94],"However,":[47],"these":[48],"ML-based":[49],"often":[51],"suffer":[52],"from":[53],"lack":[55],"interpretability":[57],"or":[58],"are":[59],"restricted":[60,143],"by":[61],"predefined":[62,145],"mathematical":[63],"operators,":[64],"limiting":[65],"their":[66],"ability":[67],"mine":[69],"novel":[70],"and":[71,116,122,171],"effective":[72],"factors.":[73],"this":[75],"paper,":[76],"we":[77,124,149],"propose":[78],"FactorMAD,":[79],"multi-agent":[81,181],"debate":[82,182],"framework":[83,99],"large":[86],"language":[87],"models":[88],"(LLMs)":[89],"for":[90,187],"interpretable":[91],"Unlike":[95],"existing":[96,163],"methods,":[97],"our":[98],"employs":[100],"two":[101],"specialized":[102],"LLM":[103],"agents":[104],"that":[105,131,159],"iteratively":[106],"refine":[107],"through":[109],"structured":[110],"debate,":[111],"leveraging":[112],"diverse":[113],"prior":[114],"perspectives":[115],"critiques.":[117],"flexibility":[121],"expressiveness,":[123],"develop":[125],"code-based":[127],"development":[129],"pipeline":[130],"allows":[132],"LLMs":[133],"directly":[135],"produce":[136],"implementable":[137],"code":[139],"instead":[140],"being":[142],"operator":[146],"sets.":[147],"Empirically,":[148],"conduct":[150],"extensive":[151],"experiments":[152],"real-world":[154],"market":[156],"data,":[157],"demonstrating":[158],"FactorMAD":[160],"significantly":[161],"outperforms":[162],"predictive":[169],"performance":[170],"trading":[172],"profitability.":[173],"Our":[174],"findings":[175],"highlight":[176],"potential":[178],"LLM-driven":[180],"as":[183],"powerful":[185],"paradigm":[186],"high-quality":[189],"markets.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-11-14T00:00:00"}