{"id":"https://openalex.org/W2911517843","doi":"https://doi.org/10.1145/3308558.3313694","title":"Predictive Crawling for Commercial Web Content","display_name":"Predictive Crawling for Commercial Web Content","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2911517843","doi":"https://doi.org/10.1145/3308558.3313694","mag":"2911517843"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313694","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3308558.3313694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","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/A5071179467","display_name":"Shuguang Han","orcid":"https://orcid.org/0000-0003-1416-6960"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuguang Han","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042628219","display_name":"Bernhard Brodowsky","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bernhard Brodowsky","raw_affiliation_strings":["Google, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070532256","display_name":"Przemek Gajda","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Przemek Gajda","raw_affiliation_strings":["Google, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028327226","display_name":"S. P. Novikov","orcid":"https://orcid.org/0000-0002-3981-7873"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sergey Novikov","raw_affiliation_strings":["Google, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109603969","display_name":"Mike Bendersky","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Bendersky","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037200145","display_name":"Marc Najork","orcid":"https://orcid.org/0000-0003-1423-0854"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Najork","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015275752","display_name":"Robin Dua","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robin Dua","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027411355","display_name":"Alexandrin Popescul","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandrin Popescul","raw_affiliation_strings":["Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.116,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8977148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"627","last_page":"637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9732999801635742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8441337943077087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.76253342628479},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7002106308937073},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.6971439719200134},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5657830834388733},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5349354147911072},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4448857605457306},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.41492801904678345},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3137736916542053}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8441337943077087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76253342628479},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7002106308937073},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.6971439719200134},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5657830834388733},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5349354147911072},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4448857605457306},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.41492801904678345},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3137736916542053},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3308558.3313694","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3308558.3313694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W757809383","https://openalex.org/W1484417080","https://openalex.org/W1566984846","https://openalex.org/W1660264423","https://openalex.org/W1938006511","https://openalex.org/W1968297936","https://openalex.org/W1970841368","https://openalex.org/W1976624301","https://openalex.org/W1987272746","https://openalex.org/W1988497390","https://openalex.org/W2016122268","https://openalex.org/W2029341294","https://openalex.org/W2030453570","https://openalex.org/W2038378248","https://openalex.org/W2059713800","https://openalex.org/W2080901490","https://openalex.org/W2118129497","https://openalex.org/W2123585936","https://openalex.org/W2127536142","https://openalex.org/W2140279085","https://openalex.org/W2142211218","https://openalex.org/W2148931201","https://openalex.org/W2151932833","https://openalex.org/W2165862792","https://openalex.org/W2169557227","https://openalex.org/W2189162242","https://openalex.org/W2402441596","https://openalex.org/W2475334473","https://openalex.org/W2884612586","https://openalex.org/W2911388033","https://openalex.org/W2950577311","https://openalex.org/W2953384591","https://openalex.org/W4251434705","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114"],"abstract_inverted_index":{"Web":[0],"crawlers":[1],"spend":[2],"significant":[3],"resources":[4,18],"to":[5,19,45,52,59,74,78],"maintain":[6],"freshness":[7],"of":[8,17,30,49,81,108],"their":[9],"crawled":[10],"data.":[11,117],"This":[12],"paper":[13],"describes":[14],"the":[15,47,65,68,106],"optimization":[16],"ensure":[20],"that":[21,120],"product":[22,102],"prices":[23],"shown":[24],"in":[25,27,94,126],"ads":[26],"a":[28,31,54],"context":[29],"shopping":[32],"sponsored":[33],"search":[34],"service":[35],"are":[36,43],"synchronized":[37],"with":[38],"current":[39],"merchant":[40],"prices.":[41],"We":[42,70,118],"able":[44],"use":[46],"predictability":[48],"price":[50,82],"changes":[51],"build":[53],"machine":[55,89],"learned":[56,90],"system":[57],"leading":[58],"considerable":[60],"resource":[61],"savings":[62],"for":[63],"both":[64],"merchants":[66],"and":[67,92,111],"crawler.":[69],"describe":[71],"our":[72,109,121],"solution":[73],"technical":[75],"challenges":[76],"due":[77],"partial":[79],"observability":[80],"history,":[83],"feedback":[84],"loops":[85],"arising":[86],"from":[87],"applying":[88],"models,":[91],"offers":[93],"cold":[95],"start":[96],"state.":[97],"Empirical":[98],"evaluation":[99],"over":[100],"large-scale":[101],"crawl":[103],"data":[104,129],"demonstrates":[105],"effectiveness":[107],"model":[110],"confirms":[112],"its":[113],"robustness":[114],"towards":[115],"unseen":[116],"argue":[119],"approach":[122],"can":[123],"be":[124],"applicable":[125],"more":[127],"general":[128],"pull":[130],"settings.":[131]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
