{"id":"https://openalex.org/W4293211490","doi":"https://doi.org/10.1109/tai.2022.3186292","title":"An Automated Deep Reinforcement Learning Pipeline for Dynamic Pricing","display_name":"An Automated Deep Reinforcement Learning Pipeline for Dynamic Pricing","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4293211490","doi":"https://doi.org/10.1109/tai.2022.3186292"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2022.3186292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3186292","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/206634982/vPublished.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019907650","display_name":"Reza Refaei Afshar","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Reza Refaei Afshar","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062973890","display_name":"Jason Rhuggenaath","orcid":"https://orcid.org/0000-0001-5368-2947"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jason Rhuggenaath","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077147157","display_name":"Yingqian Zhang","orcid":"https://orcid.org/0000-0002-5073-0787"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yingqian Zhang","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080242338","display_name":"Uzay Kaymak","orcid":"https://orcid.org/0000-0002-4500-9098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uzay Kaymak","raw_affiliation_strings":["Jheronimus Academy of Data Science, ‘s-Hertogenbosch, Netherlands"],"affiliations":[{"raw_affiliation_string":"Jheronimus Academy of Data Science, ‘s-Hertogenbosch, Netherlands","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019907650"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":1.5967,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84968895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"4","issue":"3","first_page":"428","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9979000091552734,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7914676070213318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6932872533798218},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6385121941566467},{"id":"https://openalex.org/keywords/bidding","display_name":"Bidding","score":0.5537093877792358},{"id":"https://openalex.org/keywords/dynamic-pricing","display_name":"Dynamic pricing","score":0.5514720678329468},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5269563794136047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5247057676315308},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.510123074054718},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.49041080474853516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47463974356651306},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46668514609336853},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.46639224886894226},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43828126788139343},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4142155945301056},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3402014970779419},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.30996206402778625}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7914676070213318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6932872533798218},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6385121941566467},{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.5537093877792358},{"id":"https://openalex.org/C2779391423","wikidata":"https://www.wikidata.org/wiki/Q17009728","display_name":"Dynamic pricing","level":2,"score":0.5514720678329468},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5269563794136047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5247057676315308},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.510123074054718},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.49041080474853516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47463974356651306},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46668514609336853},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.46639224886894226},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43828126788139343},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4142155945301056},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3402014970779419},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.30996206402778625},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":4,"locations":[{"id":"doi:10.1109/tai.2022.3186292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3186292","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:openaire/df62b628-5478-48f1-ac64-cc389bdc8b5f","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/df62b628-5478-48f1-ac64-cc389bdc8b5f","pdf_url":"https://pure.tue.nl/ws/files/206634982/vPublished.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Refaei Afshar, R, Rhuggenaath, J, Zhang, Y & Kaymak, U 2023, 'An Automated Deep Reinforcement Learning Pipeline for Dynamic Pricing', IEEE Transactions on Artificial Intelligence, vol. 4, no. 3, pp. 428-437. https://doi.org/10.1109/TAI.2022.3186292","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.tue.nl:publications/df62b628-5478-48f1-ac64-cc389bdc8b5f","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85133739199&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Refaei Afshar, R, Rhuggenaath, J, Zhang, Y & Kaymak, U 2023, 'An Automated Deep Reinforcement Learning Pipeline for Dynamic Pricing', IEEE Transactions on Artificial Intelligence, vol. 4, no. 3, pp. 428-437. https://doi.org/10.1109/TAI.2022.3186292","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:tue:oai:pure.tue.nl:publications/df62b628-5478-48f1-ac64-cc389bdc8b5f","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/df62b628-5478-48f1-ac64-cc389bdc8b5f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Artificial Intelligence, 4(3), 428 - 437. Institute of Electrical and Electronics Engineers","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire/df62b628-5478-48f1-ac64-cc389bdc8b5f","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/df62b628-5478-48f1-ac64-cc389bdc8b5f","pdf_url":"https://pure.tue.nl/ws/files/206634982/vPublished.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Refaei Afshar, R, Rhuggenaath, J, Zhang, Y & Kaymak, U 2023, 'An Automated Deep Reinforcement Learning Pipeline for Dynamic Pricing', IEEE Transactions on Artificial Intelligence, vol. 4, no. 3, pp. 428-437. https://doi.org/10.1109/TAI.2022.3186292","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338388","display_name":"Eurostars","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293211490.pdf","grobid_xml":"https://content.openalex.org/works/W4293211490.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1522248029","https://openalex.org/W2299115575","https://openalex.org/W2564077743","https://openalex.org/W2740828027","https://openalex.org/W2758709491","https://openalex.org/W2767534831","https://openalex.org/W2769108999","https://openalex.org/W2788125442","https://openalex.org/W2912063360","https://openalex.org/W2921600809","https://openalex.org/W2946531308","https://openalex.org/W2952536678","https://openalex.org/W2956404547","https://openalex.org/W2963749556","https://openalex.org/W2968917487","https://openalex.org/W2985423386","https://openalex.org/W2996947519","https://openalex.org/W2997902164","https://openalex.org/W2998596932","https://openalex.org/W3018179997","https://openalex.org/W3082514436","https://openalex.org/W3103752844","https://openalex.org/W3123482145","https://openalex.org/W3123573640","https://openalex.org/W3126095556","https://openalex.org/W3167696941","https://openalex.org/W3175901868","https://openalex.org/W3196282477","https://openalex.org/W4226145847","https://openalex.org/W4287673640","https://openalex.org/W4312360278","https://openalex.org/W6697873463","https://openalex.org/W6725207838","https://openalex.org/W6741471465","https://openalex.org/W6747985145","https://openalex.org/W6763153117","https://openalex.org/W6776395528","https://openalex.org/W6782355921","https://openalex.org/W6810915194"],"related_works":["https://openalex.org/W4233965824","https://openalex.org/W2607442583","https://openalex.org/W3199199693","https://openalex.org/W4286970057","https://openalex.org/W2995583237","https://openalex.org/W2967237190","https://openalex.org/W4323366554","https://openalex.org/W3028852288","https://openalex.org/W4221150662","https://openalex.org/W2405673391"],"abstract_inverted_index":{"A":[0],"dynamic":[1,10,40,77],"pricing":[2,41,169],"problem":[3],"is":[4,28,47,64,171,175,184],"difficult":[5],"due":[6],"to":[7,104],"the":[8,34,50,117,132,136,160,179,191,200],"highly":[9],"environment":[11,194],"and":[12,59,95,107,131],"unknown":[13],"demand":[14],"distributions.":[15],"In":[16],"this":[17],"article,":[18],"we":[19],"propose":[20],"a":[21,29,39,112,122,153,168,188],"deep":[22],"reinforcement":[23,201],"learning":[24,202],"(DRL)":[25],"framework,":[26],"which":[27],"pipeline":[30,46,81,143],"that":[31,127,158,195],"automatically":[32],"defines":[33],"DRL":[35,45,51,75,80,86,142,161,166],"components":[36],"for":[37,76,190,199],"solving":[38],"problem.":[42],"The":[43,66,182],"automated":[44],"necessary":[48],"because":[49],"framework":[52],"can":[53],"be":[54],"designed":[55],"in":[56,149],"numerous":[57],"ways,":[58],"manually":[60],"finding":[61],"optimal":[62],"configurations":[63],"tedious.":[65],"levels":[67],"of":[68,73,85,135],"automation":[69],"make":[70],"nonexperts":[71],"capable":[72],"using":[74,111,121,159],"pricing.":[78],"Our":[79],"contains":[82],"three":[83],"steps":[84],"design,":[87],"including":[88],"Markov":[89],"decision":[90],"process":[91],"modeling,":[92],"algorithm":[93],"selection,":[94],"hyperparameter":[96,124],"optimization.":[97],"It":[98],"starts":[99],"with":[100],"transforming":[101],"available":[102],"information":[103],"state":[105],"representation":[106],"defining":[108],"reward":[109,113],"function":[110],"shaping":[114],"approach.":[115],"Then,":[116],"hyperparameters":[118],"are":[119],"tuned":[120],"novel":[123],"optimization":[125,130,147],"method":[126],"integrates":[128],"Bayesian":[129],"selection":[133],"operator":[134],"genetic":[137],"algorithm.":[138],"We":[139,156],"employ":[140],"our":[141,165],"on":[144],"reserve":[145],"price":[146],"problems":[148],"online":[150],"advertising":[151],"as":[152],"case":[154],"study.":[155],"show":[157],"configuration":[162],"obtained":[163,172],"by":[164,186],"pipeline,":[167],"policy":[170],"whose":[173],"revenue":[174],"significantly":[176],"higher":[177],"than":[178],"benchmark":[180],"methods.":[181],"evaluation":[183],"performed":[185],"developing":[187],"simulation":[189],"real-time":[192],"bidding":[193],"makes":[196],"exploration":[197],"possible":[198],"agent.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}