{"id":"https://openalex.org/W4318242471","doi":"https://doi.org/10.48550/arxiv.2301.10724","title":"Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning","display_name":"Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-25","ids":{"openalex":"https://openalex.org/W4318242471","doi":"https://doi.org/10.48550/arxiv.2301.10724"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2301.10724","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.10724","pdf_url":"https://arxiv.org/pdf/2301.10724","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.10724","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054465909","display_name":"Weiguang Han","orcid":"https://orcid.org/0000-0003-1821-4667"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Han, Weiguang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005535515","display_name":"Boyi Zhang","orcid":"https://orcid.org/0000-0002-1956-7424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Boyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868563","display_name":"Qianqian Xie","orcid":"https://orcid.org/0000-0002-9588-7454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Qianqian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089527851","display_name":"Min Peng","orcid":"https://orcid.org/0000-0002-0901-3102"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Min","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029848442","display_name":"Yanzhao Lai","orcid":"https://orcid.org/0000-0002-8067-0842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Yanzhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018254776","display_name":"Jimin Huang","orcid":"https://orcid.org/0000-0002-3501-3907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jimin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054465909"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10047","display_name":"Financial Markets and Investment Strategies","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10047","display_name":"Financial Markets and Investment Strategies","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.998199999332428,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9747999906539917,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7009933590888977},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6696091890335083},{"id":"https://openalex.org/keywords/trading-strategy","display_name":"Trading strategy","score":0.6492976546287537},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6405609846115112},{"id":"https://openalex.org/keywords/pairs-trade","display_name":"Pairs trade","score":0.6126657128334045},{"id":"https://openalex.org/keywords/statistical-arbitrage","display_name":"Statistical arbitrage","score":0.4817812144756317},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47486209869384766},{"id":"https://openalex.org/keywords/high-frequency-trading","display_name":"High-frequency trading","score":0.43089836835861206},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.424155056476593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42055103182792664},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.4200507402420044},{"id":"https://openalex.org/keywords/algorithmic-trading","display_name":"Algorithmic trading","score":0.4139784276485443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38845378160476685},{"id":"https://openalex.org/keywords/alternative-trading-system","display_name":"Alternative trading system","score":0.2754828929901123},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.230226069688797},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.1870008409023285},{"id":"https://openalex.org/keywords/financial-economics","display_name":"Financial economics","score":0.16139832139015198},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1437748372554779},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09953328967094421},{"id":"https://openalex.org/keywords/capital-asset-pricing-model","display_name":"Capital asset pricing model","score":0.09666237235069275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009933590888977},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6696091890335083},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.6492976546287537},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6405609846115112},{"id":"https://openalex.org/C158876240","wikidata":"https://www.wikidata.org/wiki/Q17105131","display_name":"Pairs trade","level":4,"score":0.6126657128334045},{"id":"https://openalex.org/C167416602","wikidata":"https://www.wikidata.org/wiki/Q2859660","display_name":"Statistical arbitrage","level":5,"score":0.4817812144756317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47486209869384766},{"id":"https://openalex.org/C24683644","wikidata":"https://www.wikidata.org/wiki/Q138372","display_name":"High-frequency trading","level":3,"score":0.43089836835861206},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.424155056476593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42055103182792664},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.4200507402420044},{"id":"https://openalex.org/C78508483","wikidata":"https://www.wikidata.org/wiki/Q139445","display_name":"Algorithmic trading","level":2,"score":0.4139784276485443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38845378160476685},{"id":"https://openalex.org/C172428447","wikidata":"https://www.wikidata.org/wiki/Q438711","display_name":"Alternative trading system","level":3,"score":0.2754828929901123},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.230226069688797},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.1870008409023285},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.16139832139015198},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1437748372554779},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09953328967094421},{"id":"https://openalex.org/C181236170","wikidata":"https://www.wikidata.org/wiki/Q848354","display_name":"Capital asset pricing model","level":2,"score":0.09666237235069275},{"id":"https://openalex.org/C142450864","wikidata":"https://www.wikidata.org/wiki/Q629941","display_name":"Arbitrage pricing theory","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C42854785","wikidata":"https://www.wikidata.org/wiki/Q2154735","display_name":"Risk arbitrage","level":4,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2301.10724","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.10724","pdf_url":"https://arxiv.org/pdf/2301.10724","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:RePEc:arx:papers:2301.10724","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"preprint"},{"id":"doi:10.48550/arxiv.2301.10724","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.10724","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.10724","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.10724","pdf_url":"https://arxiv.org/pdf/2301.10724","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318242471.pdf","grobid_xml":"https://content.openalex.org/works/W4318242471.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1574922981","https://openalex.org/W2392556764","https://openalex.org/W2521336015","https://openalex.org/W1552949382","https://openalex.org/W4250178512","https://openalex.org/W2760714711","https://openalex.org/W2291727600","https://openalex.org/W1780554743","https://openalex.org/W2988746083","https://openalex.org/W2785550510"],"abstract_inverted_index":{"Pair":[0],"trading":[1,60,78,105,150,166,174],"is":[2],"one":[3],"of":[4,20,40,89,149,161],"the":[5,27,38,59,64,74,82,159],"most":[6],"effective":[7],"statistical":[8],"arbitrage":[9],"strategies":[10],"which":[11],"seeks":[12],"a":[13,18,100,107,112,117,141,147],"neutral":[14],"profit":[15],"by":[16],"hedging":[17],"pair":[19,33,56,104,165,171],"selected":[21,68,83],"assets.":[22,91],"Existing":[23],"methods":[24],"generally":[25],"decompose":[26],"task":[28,109],"into":[29],"two":[30,41,127,134],"separate":[31],"steps:":[32],"selection":[34,172],"and":[35,49,125,140,173],"trading.":[36],"However,":[37],"decoupling":[39],"closely":[42],"related":[43],"subtasks":[44],"can":[45,79],"block":[46],"information":[47,88],"propagation":[48],"lead":[50],"to":[51,81,122],"limited":[52],"overall":[53],"performance.":[54],"For":[55],"selection,":[57],"ignoring":[58],"performance":[61],"results":[62,153],"in":[63,95],"wrong":[65],"assets":[66,84,135],"being":[67],"with":[69,168],"irrelevant":[70],"price":[71],"movements,":[72],"while":[73],"agent":[75],"trained":[76],"for":[77,102],"overfit":[80],"without":[85],"any":[86],"historical":[87],"other":[90],"To":[92],"address":[93],"it,":[94],"this":[96],"paper,":[97],"we":[98],"propose":[99],"paradigm":[101],"automatic":[103],"as":[106],"unified":[108],"rather":[110],"than":[111],"two-step":[113],"pipeline.":[114],"We":[115],"design":[116],"hierarchical":[118],"reinforcement":[119],"learning":[120],"framework":[121],"jointly":[123],"learn":[124],"optimize":[126],"subtasks.":[128],"A":[129],"high-level":[130],"policy":[131,143],"would":[132,144],"select":[133],"from":[136],"all":[137],"possible":[138],"combinations":[139],"low-level":[142],"then":[145],"perform":[146],"series":[148],"actions.":[151],"Experimental":[152],"on":[154,164],"real-world":[155],"stock":[156],"data":[157],"demonstrate":[158],"effectiveness":[160],"our":[162],"method":[163],"compared":[167],"both":[169],"existing":[170],"methods.":[175]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2023-01-27T00:00:00"}