{"id":"https://openalex.org/W2073108794","doi":"https://doi.org/10.1145/1871437.1871606","title":"Efficiently querying archived data using Hadoop","display_name":"Efficiently querying archived data using Hadoop","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2073108794","doi":"https://doi.org/10.1145/1871437.1871606","mag":"2073108794"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103206130","display_name":"Rajeev Gupta","orcid":"https://orcid.org/0000-0002-5615-0361"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajeev Gupta","raw_affiliation_strings":["IBM Research, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101643160","display_name":"Himanshu Gupta","orcid":"https://orcid.org/0000-0003-3271-3032"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshu Gupta","raw_affiliation_strings":["IBM Research, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079953945","display_name":"Ullas Nambiar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ullas Nambiar","raw_affiliation_strings":["IBM Research, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukesh Mohania","raw_affiliation_strings":["IBM Research, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1301","last_page":"1304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983000159263611,"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/T11106","display_name":"Data Management and Algorithms","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8266757130622864},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.803895115852356},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5879632234573364},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5744903683662415},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"Business intelligence","score":0.5241473317146301},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.502065896987915},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49812889099121094},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.46302810311317444},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.45809775590896606},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43298614025115967},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.4267263412475586},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2817752957344055},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2037944495677948},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13716447353363037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266757130622864},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.803895115852356},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5879632234573364},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5744903683662415},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.5241473317146301},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.502065896987915},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49812889099121094},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.46302810311317444},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.45809775590896606},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43298614025115967},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.4267263412475586},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2817752957344055},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2037944495677948},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13716447353363037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2125366406","https://openalex.org/W2152603468","https://openalex.org/W3138367763","https://openalex.org/W6682612399"],"related_works":["https://openalex.org/W208715492","https://openalex.org/W2581040172","https://openalex.org/W2383696629","https://openalex.org/W2506063602","https://openalex.org/W23190051","https://openalex.org/W2362581214","https://openalex.org/W3165010183","https://openalex.org/W2953652248","https://openalex.org/W2901498424","https://openalex.org/W4248501364"],"abstract_inverted_index":{"The":[0],"need":[1],"to":[2,30,47,60,102],"analyze":[3],"structured":[4,116],"data":[5,33,44,50,56,73,91,105,117],"for":[6,75,90,139],"various":[7,115],"business":[8],"intelligence":[9],"applications":[10],"such":[11,32],"as":[12],"customer":[13],"churn":[14],"analysis,":[15,18],"social":[16],"network":[17,20],"telecom":[19],"monitoring":[21],"etc.,":[22],"is":[23,136],"well":[24],"known.":[25],"However,":[26],"the":[27,53,58,71,104,140],"potential":[28],"size":[29],"which":[31],"will":[34,38],"scale":[35],"in":[36,106],"future":[37],"make":[39,70],"solutions":[40],"that":[41,93,126],"revolve":[42],"around":[43],"warehouses":[45,92],"hard":[46],"scale.":[48],"As":[49],"sizes":[51],"grow":[52],"movement":[54],"of":[55,78,96,129],"from":[57],"warehouse":[59],"archives":[61],"becomes":[62],"more":[63],"frequent.":[64],"Current":[65],"file":[66,99],"based":[67],"archive":[68],"models":[69],"archived":[72],"unusable":[74],"any":[76],"type":[77],"insight":[79],"extraction.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"present":[85],"an":[86,107],"active":[87,141],"archival":[88,142],"solution":[89],"makes":[94],"use":[95],"Hadoop":[97],"distributed":[98],"system":[100],"(HDFS)":[101],"store":[103,135],"always":[108],"available":[109],"and":[110,122,133],"cost-effective":[111],"manner.":[112],"We":[113],"investigate":[114],"storage":[118],"schemes":[119],"within":[120],"HDFS":[121],"empirical":[123],"evaluations":[124],"show":[125],"a":[127],"combination":[128],"Universal":[130],"scheme":[131],"model":[132],"column":[134],"best":[137],"suited":[138],"solution.":[143]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
