{"id":"https://openalex.org/W2973198305","doi":"https://doi.org/10.1145/3298689.3347002","title":"Addressing delayed feedback for continuous training with neural networks in CTR prediction","display_name":"Addressing delayed feedback for continuous training with neural networks in CTR prediction","publication_year":2019,"publication_date":"2019-09-10","ids":{"openalex":"https://openalex.org/W2973198305","doi":"https://doi.org/10.1145/3298689.3347002","mag":"2973198305"},"language":"en","primary_location":{"id":"doi:10.1145/3298689.3347002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3298689.3347002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM Conference on Recommender Systems","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/A5074861404","display_name":"Sofia Ira Ktena","orcid":"https://orcid.org/0000-0001-6677-6547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sofia Ira Ktena","raw_affiliation_strings":["Twitter, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061046370","display_name":"Alykhan Tejani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alykhan Tejani","raw_affiliation_strings":["Twitter, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113166350","display_name":"Lucas Theis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Theis","raw_affiliation_strings":["Twitter, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029839691","display_name":"Pranay Kumar Myana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pranay Kumar Myana","raw_affiliation_strings":["Twitter, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071533815","display_name":"Deepak Dilipkumar","orcid":null},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepak Dilipkumar","raw_affiliation_strings":["Twitter"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter","institution_ids":["https://openalex.org/I113979032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052054395","display_name":"Ferenc Husz\u00e1r","orcid":"https://orcid.org/0000-0002-4988-1430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ferenc Husz\u00e1r","raw_affiliation_strings":["Twitter, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029762761","display_name":"Steven Yoo","orcid":null},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Yoo","raw_affiliation_strings":["Twitter"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter","institution_ids":["https://openalex.org/I113979032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018244514","display_name":"Wenzhe Shi","orcid":"https://orcid.org/0000-0002-9750-6379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhe Shi","raw_affiliation_strings":["Twitter, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter, London, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9044,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.94945442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9994999766349792,"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/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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/computer-science","display_name":"Computer science","score":0.7736093997955322},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7638193964958191},{"id":"https://openalex.org/keywords/display-advertising","display_name":"Display advertising","score":0.7229613661766052},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5864650011062622},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5676326155662537},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5572682023048401},{"id":"https://openalex.org/keywords/click-through-rate","display_name":"Click-through rate","score":0.5194146633148193},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5016891956329346},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4888860285282135},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4713803231716156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46996089816093445},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4455735981464386},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4363762140274048},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4251026511192322},{"id":"https://openalex.org/keywords/online-advertising","display_name":"Online advertising","score":0.1862829029560089},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.11748141050338745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736093997955322},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7638193964958191},{"id":"https://openalex.org/C2777999536","wikidata":"https://www.wikidata.org/wiki/Q2399498","display_name":"Display advertising","level":4,"score":0.7229613661766052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5864650011062622},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5676326155662537},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5572682023048401},{"id":"https://openalex.org/C115174607","wikidata":"https://www.wikidata.org/wiki/Q1100934","display_name":"Click-through rate","level":2,"score":0.5194146633148193},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5016891956329346},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4888860285282135},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4713803231716156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46996089816093445},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4455735981464386},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4363762140274048},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4251026511192322},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.1862829029560089},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.11748141050338745},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3298689.3347002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3298689.3347002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1825821140","https://openalex.org/W1976517433","https://openalex.org/W2021866613","https://openalex.org/W2044425952","https://openalex.org/W2049633694","https://openalex.org/W2050871273","https://openalex.org/W2076618162","https://openalex.org/W2101571195","https://openalex.org/W2110818436","https://openalex.org/W2117864026","https://openalex.org/W2122124659","https://openalex.org/W2123958887","https://openalex.org/W2132442585","https://openalex.org/W2133227149","https://openalex.org/W2139759436","https://openalex.org/W2141570612","https://openalex.org/W2146807976","https://openalex.org/W2158685856","https://openalex.org/W2159566498","https://openalex.org/W2475334473","https://openalex.org/W2509235963","https://openalex.org/W2560647685","https://openalex.org/W2724479291","https://openalex.org/W2730527299","https://openalex.org/W2902572901","https://openalex.org/W2963341628","https://openalex.org/W2963739929","https://openalex.org/W3009804075"],"related_works":["https://openalex.org/W3085284911","https://openalex.org/W2100597815","https://openalex.org/W3155121005","https://openalex.org/W1995609428","https://openalex.org/W3190524507","https://openalex.org/W2211399443","https://openalex.org/W3000197790","https://openalex.org/W1910640298","https://openalex.org/W3121131658","https://openalex.org/W175164097"],"abstract_inverted_index":{"One":[0],"of":[1,11,139,148,161,166,179],"the":[2,9,98,104,145,164,186,213,233],"challenges":[3],"in":[4,52,61,86,128,163,193,202,222,237,243,276],"display":[5],"advertising":[6],"is":[7,43,142],"that":[8,153],"distribution":[10],"features":[12],"and":[13,31,74,132,151,199,206],"click":[14],"through":[15],"rate":[16],"(CTR)":[17],"can":[18],"exhibit":[19],"large":[20],"shifts":[21,42],"over":[22],"time":[23,99],"due":[24],"to":[25,28,37,44,54,83,124,143,182,239],"seasonality,":[26],"changes":[27],"ad":[29,63],"campaigns":[30],"other":[32],"factors.":[33],"The":[34,137],"predominant":[35],"strategy":[36],"keep":[38],"up":[39],"with":[40,204,217,232],"these":[41],"train":[45],"predictive":[46],"models":[47,152],"continuously,":[48],"on":[49,196,250],"fresh":[50,89],"data,":[51],"order":[53,238],"prevent":[55],"them":[56,180],"from":[57,157],"becoming":[58],"stale.":[59],"However,":[60],"many":[62],"systems":[64],"positive":[65,119],"labels":[66,79],"are":[67,101],"only":[68],"observed":[69,273],"after":[70],"a":[71,81,114,118,158,223,244],"possibly":[72],"long":[73],"random":[75],"delay.":[76],"These":[77],"delayed":[78,167],"pose":[80],"challenge":[82],"data":[84,90,112,162,254],"freshness":[85],"continuous":[87,159,245],"training:":[88],"may":[91],"not":[92],"have":[93],"complete":[94],"label":[95,120],"information":[96],"at":[97],"they":[100],"ingested":[102],"by":[103,263],"training":[105,246,249],"algorithm.":[106],"Naive":[107],"strategies":[108],"which":[109],"consider":[110],"any":[111],"point":[113],"negative":[115],"example":[116],"until":[117],"becomes":[121],"available":[122],"tend":[123],"underestimate":[125],"CTR,":[126],"resulting":[127],"inferior":[129],"user":[130],"experience":[131],"suboptimal":[133],"performance":[134,192,242],"for":[135,185],"advertisers.":[136],"focus":[138],"this":[140,170,183],"paper":[141],"identify":[144],"best":[146],"combination":[147],"loss":[149,176,220],"functions":[150],"enable":[154],"large-scale":[155],"learning":[156],"stream":[160],"presence":[165],"labels.":[168],"In":[169],"work,":[171],"we":[172,227,272],"compare":[173],"5":[174],"different":[175],"functions,":[177],"3":[178],"applied":[181],"problem":[184],"first":[187],"time.":[188],"We":[189,210],"benchmark":[190],"their":[191,241],"offline":[194],"settings":[195],"both":[197],"public":[198],"proprietary":[200],"datasets":[201],"conjunction":[203],"shallow":[205],"deep":[207],"model":[208],"architectures.":[209],"also":[211],"discuss":[212],"engineering":[214],"cost":[215],"associated":[216],"implementing":[218],"each":[219],"function":[221],"production":[224],"environment.":[225],"Finally,":[226],"carried":[228],"out":[229],"online":[230,270],"experiments":[231],"top":[234],"performing":[235],"methods,":[236],"validate":[240],"scheme.":[247],"While":[248],"668":[251],"million":[252],"in-house":[253],"points":[255],"offline,":[256],"our":[257],"proposed":[258],"methods":[259],"outperform":[260],"previous":[261],"state-of-the-art":[262],"3%":[264],"relative":[265],"cross":[266],"entropy":[267],"(RCE).":[268],"During":[269],"experiments,":[271],"55%":[274],"gain":[275],"revenue":[277],"per":[278],"thousand":[279],"requests":[280],"(RPMq)":[281],"against":[282],"naive":[283],"log":[284],"loss.":[285]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}