{"id":"https://openalex.org/W2964108915","doi":"https://doi.org/10.1145/3219819.3219846","title":"Reinforcement Learning to Rank in E-Commerce Search Engine","display_name":"Reinforcement Learning to Rank in E-Commerce Search Engine","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2964108915","doi":"https://doi.org/10.1145/3219819.3219846","mag":"2964108915"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3219846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3219846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/A5104264364","display_name":"Yujing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Hu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070849903","display_name":"Qing Da","orcid":"https://orcid.org/0000-0003-2200-0098"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Da","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076875538","display_name":"Anxiang Zeng","orcid":"https://orcid.org/0000-0003-3869-5357"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anxiang Zeng","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110763379","display_name":"Yinghui Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghui Xu","raw_affiliation_strings":["Zhejiang Cainiao Supply Chain Management Co., Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Cainiao Supply Chain Management Co., Ltd., Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.0536,"has_fulltext":false,"cited_by_count":148,"citation_normalized_percentile":{"value":0.99440682,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"368","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9980000257492065,"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/T11182","display_name":"Auction Theory and Applications","score":0.9980000257492065,"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/T12288","display_name":"Optimization and Search Problems","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.800442099571228},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7780817747116089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7254072427749634},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.621179461479187},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5951086282730103},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5643995404243469},{"id":"https://openalex.org/keywords/ranking-svm","display_name":"Ranking SVM","score":0.5291669368743896},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4920062720775604},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.48034799098968506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4800585210323334},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.47558486461639404},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4327424168586731},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.27096280455589294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1430419683456421},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10869947075843811},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10359311103820801}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.800442099571228},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7780817747116089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254072427749634},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.621179461479187},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5951086282730103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5643995404243469},{"id":"https://openalex.org/C124975894","wikidata":"https://www.wikidata.org/wiki/Q7293290","display_name":"Ranking SVM","level":3,"score":0.5291669368743896},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4920062720775604},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.48034799098968506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4800585210323334},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.47558486461639404},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4327424168586731},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27096280455589294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1430419683456421},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10869947075843811},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10359311103820801},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3219819.3219846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3219846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W1505937442","https://openalex.org/W1515851193","https://openalex.org/W1771410628","https://openalex.org/W1900560890","https://openalex.org/W1984770088","https://openalex.org/W2009979684","https://openalex.org/W2023599408","https://openalex.org/W2047221353","https://openalex.org/W2067802667","https://openalex.org/W2108114251","https://openalex.org/W2108862644","https://openalex.org/W2117600734","https://openalex.org/W2119717200","https://openalex.org/W2119850747","https://openalex.org/W2120391124","https://openalex.org/W2125398996","https://openalex.org/W2143331230","https://openalex.org/W2145339207","https://openalex.org/W2149427297","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2418554883","https://openalex.org/W2443763917","https://openalex.org/W2489939061","https://openalex.org/W2519411794","https://openalex.org/W2605800822","https://openalex.org/W2809162153","https://openalex.org/W2962980735","https://openalex.org/W2964240248","https://openalex.org/W3005391178","https://openalex.org/W3011120880","https://openalex.org/W4247950230","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W4225269853","https://openalex.org/W3168977894"],"abstract_inverted_index":{"In":[0],"E-commerce":[1],"platforms":[2],"such":[3,34],"as":[4],"Amazon":[5],"and":[6,117,152,164,186,196],"TaoBao":[7,165],",":[8],"ranking":[9,31,39,63,79,108,138],"items":[10],"in":[11,41,65,87,162,193],"a":[12,16,42,88,129],"search":[13,89,98,166],"session":[14,43,99],"is":[15,141],"typical":[17],"multi-step":[18,107],"decision-making":[19],"problem.":[20,109],"Learning":[21],"to":[22,30,44,53,70,75,104,143],"rank":[23],"(LTR)":[24],"methods":[25,35],"have":[26],"been":[27],"widely":[28],"applied":[29],"problems.":[32],"However,":[33],"often":[36],"consider":[37],"different":[38,62],"steps":[40],"be":[45,50],"independent,":[46],"which":[47,81,140],"conversely":[48],"may":[49],"highly":[51],"correlated":[52],"each":[54],"other.":[55],"For":[56],"better":[57,176],"utilizing":[58],"the":[59,83,95,106,113,120,146,178,194,197],"correlation":[60],"between":[61],"steps,":[64],"this":[66],"paper,":[67],"we":[68,92,111,127],"propose":[69,128],"use":[71],"reinforcement":[72],"learning":[73,135],"(RL)":[74],"learn":[76],"an":[77,136,157],"optimal":[78,137],"policy":[80,131],"maximizes":[82],"expected":[84],"accumulative":[85,124],"rewards":[86],"session.":[90],"Firstly,":[91],"formally":[93],"define":[94],"concept":[96],"of":[97,115,122,148,156,189],"Markov":[100],"decision":[101],"process":[102],"(SSMDP)":[103],"formulate":[105],"Secondly,":[110],"analyze":[112],"property":[114],"SSMDP":[116],"theoretically":[118],"prove":[119],"necessity":[121],"maximizing":[123],"rewards.":[125],"Lastly,":[126],"novel":[130],"gradient":[132],"algorithm":[133,173],"for":[134],"policy,":[139],"able":[142],"deal":[144],"with":[145,182],"problem":[147],"high":[149],"reward":[150,154],"variance":[151],"unbalanced":[153],"distribution":[155],"SSMDP.":[158],"Experiments":[159],"are":[160],"conducted":[161],"simulation":[163,195],"engine.":[167],"The":[168],"results":[169],"demonstrate":[170],"that":[171],"our":[172],"performs":[174],"much":[175],"than":[177,184],"state-of-the-art":[179],"LTR":[180],"methods,":[181],"more":[183],"40%":[185],"30%":[187],"growth":[188],"total":[190],"transaction":[191],"amount":[192],"real":[198],"application,":[199],"respectively.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}