{"id":"https://openalex.org/W4312272635","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892333","title":"Solving the optimal stopping problem with reinforcement learning: an application in financial option exercise","display_name":"Solving the optimal stopping problem with reinforcement learning: an application in financial option exercise","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312272635","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892333"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892333","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5072900947","display_name":"Leonardo Kanashiro Felizardo","orcid":"https://orcid.org/0000-0002-2871-860X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonardo Kanashiro Felizardo","raw_affiliation_strings":["Escola Politécnica, Universidade de são Paulo,Dept. Electronic Systems,São Paulo,Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2871-860X","affiliations":[{"raw_affiliation_string":"Escola Politécnica, Universidade de são Paulo,Dept. Electronic Systems,São Paulo,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019594266","display_name":"\u00c9lia Yathie Matsumoto","orcid":"https://orcid.org/0000-0003-1667-4221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elia Matsumoto","raw_affiliation_strings":["Politécnica, Universidade de são Paulo,Dept. Electronic Systems Escola,São Paulo,Brazil"],"raw_orcid":"https://orcid.org/0000-0003-1667-4221","affiliations":[{"raw_affiliation_string":"Politécnica, Universidade de são Paulo,Dept. Electronic Systems Escola,São Paulo,Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075798143","display_name":"Emilio Del-Moral-Hernandez","orcid":"https://orcid.org/0000-0003-4554-168X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emilio Del-Moral-Hernandez","raw_affiliation_strings":["Escola Politécnica, Universidade de são Paulo,Dept. Electronic Systems,São Paulo,Brazil"],"raw_orcid":"https://orcid.org/0000-0003-4554-168X","affiliations":[{"raw_affiliation_string":"Escola Politécnica, Universidade de são Paulo,Dept. Electronic Systems,São Paulo,Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8511,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89473684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.9958999752998352,"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/T10067","display_name":"Stochastic processes and financial applications","score":0.9958999752998352,"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/T11976","display_name":"Capital Investment and Risk Analysis","score":0.995199978351593,"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/T11182","display_name":"Auction Theory and Applications","score":0.9865999817848206,"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":0.796852707862854},{"id":"https://openalex.org/keywords/optimal-stopping","display_name":"Optimal stopping","score":0.6918670535087585},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.5898324251174927},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5607507228851318},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5332690477371216},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5250675082206726},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4558166563510895},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.43420520424842834},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.3497762978076935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2773584723472595},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2675382196903229},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11606156826019287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796852707862854},{"id":"https://openalex.org/C99414536","wikidata":"https://www.wikidata.org/wiki/Q7098950","display_name":"Optimal stopping","level":2,"score":0.6918670535087585},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.5898324251174927},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5607507228851318},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5332690477371216},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5250675082206726},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4558166563510895},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.43420520424842834},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.3497762978076935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2773584723472595},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2675382196903229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11606156826019287},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892333","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":33,"referenced_works":["https://openalex.org/W202075749","https://openalex.org/W604762380","https://openalex.org/W1538131130","https://openalex.org/W1569512666","https://openalex.org/W1574770694","https://openalex.org/W1963748947","https://openalex.org/W1972677106","https://openalex.org/W1978434527","https://openalex.org/W1980647631","https://openalex.org/W2038107520","https://openalex.org/W2048081671","https://openalex.org/W2068496814","https://openalex.org/W2077441682","https://openalex.org/W2101926813","https://openalex.org/W2103496339","https://openalex.org/W2116360511","https://openalex.org/W2126311658","https://openalex.org/W2151029520","https://openalex.org/W2155523805","https://openalex.org/W2161915898","https://openalex.org/W2169296382","https://openalex.org/W2568888746","https://openalex.org/W2965485141","https://openalex.org/W3003677889","https://openalex.org/W3121602229","https://openalex.org/W3121938364","https://openalex.org/W3122150082","https://openalex.org/W3122396469","https://openalex.org/W3123878627","https://openalex.org/W3125233838","https://openalex.org/W3164764925","https://openalex.org/W6608357038","https://openalex.org/W6750882714"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W3038169181","https://openalex.org/W2386410636","https://openalex.org/W3080706152","https://openalex.org/W3038962357","https://openalex.org/W2080374567","https://openalex.org/W2090158052","https://openalex.org/W4285537323","https://openalex.org/W2025663273"],"abstract_inverted_index":{"The":[0],"optimal":[1,30,91,127,202],"stopping":[2,31,92,128],"problem":[3,93,156,208],"is":[4,16,72,136],"a":[5,11,65,108,142,168],"category":[6],"of":[7,49,60,77,100,165,204],"decision":[8,134],"problems":[9,135],"with":[10,153,209],"specific":[12,187],"constrained":[13],"configuration.":[14],"It":[15],"relevant":[17],"to":[18,85,116,124,132,151,199,227],"various":[19],"real-world":[20,253],"applications":[21],"such":[22,38],"as":[23,39,64],"finance":[24],"and":[25,118],"management.":[26],"To":[27],"solve":[28,125,133],"the":[29,40,57,61,70,75,89,98,101,126,154,162,183,201,205,210,228,245,252,257],"problem,":[32],"state-of-the-art":[33],"algorithms":[34],"in":[35],"dynamic":[36],"programming,":[37],"least-squares":[41],"Monte":[42,113,247],"Carlo":[43,114,248],"(LSMC),":[44],"are":[45],"employed.":[46],"This":[47],"type":[48],"algorithm":[50],"relies":[51],"on":[52,256],"path":[53],"simulations":[54,249],"using":[55],"only":[56],"last":[58],"price":[59],"underlying":[62],"asset":[63],"state":[66],"representation.":[67],"In":[68],"addition,":[69],"LSMC":[71,102,211],"designed":[73],"for":[74],"valuation":[76],"options":[78,207],"where":[79],"risk-neutral":[80],"probabilities":[81],"can":[82,219],"be":[83],"employed":[84],"explain":[86],"uncertainty.":[87],"However,":[88],"general":[90],"goals":[94],"may":[95],"not":[96,137],"fit":[97],"requirements":[99],"showing":[103],"auto-correlated":[104],"prices.":[105],"We":[106,140,171,230],"employ":[107,195],"data-driven":[109],"method":[110,198,218],"that":[111,145,157,174,176,216,250],"uses":[112,146],"simulation":[115],"train":[117],"test":[119],"artificial":[120],"neural":[121,148],"networks":[122,149],"(ANN)":[123],"problem.":[129],"Using":[130],"ANN":[131],"entirely":[138],"new.":[139],"propose":[141],"different":[143],"architecture":[144,179],"convolutional":[147],"(CNN)":[150],"deal":[152],"dimensionality":[155],"arises":[158],"when":[159,225],"we":[160,194],"transform":[161],"whole":[163],"history":[164],"prices":[166],"into":[167],"Markovian":[169],"state.":[170],"present":[172],"experiments":[173,214],"indicate":[175],"our":[177,196,217],"proposed":[178,197],"improves":[180],"results":[181],"over":[182],"previous":[184],"implementations":[185],"under":[186,244],"simulated":[188],"time":[189],"series":[190],"function":[191],"sets.":[192],"Lastly,":[193],"compare":[200],"exercise":[203,223,242],"financial":[206],"algorithm.":[212],"Our":[213],"show":[215],"capture":[220],"more":[221],"accurate":[222],"opportunities":[224],"compared":[226],"LSMC.":[229],"have":[231],"an":[232],"outstandingly":[233],"higher":[234],"(above":[235],"974%":[236],"improvement)":[237],"expected":[238],"payoff":[239],"from":[240],"these":[241],"policies":[243],"many":[246],"used":[251],"return":[254],"database":[255],"out-of-sample":[258],"(test)":[259],"data.":[260]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}