{"id":"https://openalex.org/W2020199039","doi":"https://doi.org/10.1145/2723372.2742789","title":"Large-scale Predictive Analytics in Vertica","display_name":"Large-scale Predictive Analytics in Vertica","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2020199039","doi":"https://doi.org/10.1145/2723372.2742789","mag":"2020199039"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2742789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2742789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","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/A5056323971","display_name":"Subrat Kumar Prasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shreya Prasad","raw_affiliation_strings":["HP Vertica, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Vertica, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039289055","display_name":"Arash Fard","orcid":"https://orcid.org/0000-0001-5419-3176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arash Fard","raw_affiliation_strings":["HP Vertica, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Vertica, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053508948","display_name":"Vishrut Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishrut Gupta","raw_affiliation_strings":["HP Vertica, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Vertica, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674221","display_name":"Jorge Mart\u00ednez","orcid":"https://orcid.org/0000-0001-7895-7628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorge Martinez","raw_affiliation_strings":["HP Vertica, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Vertica, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071497952","display_name":"Jeff LeFevre","orcid":"https://orcid.org/0000-0003-0834-3959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff LeFevre","raw_affiliation_strings":["HP Vertica, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Vertica, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040387192","display_name":"Vincent Xu","orcid":"https://orcid.org/0000-0002-4562-4824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Xu","raw_affiliation_strings":["HP Vertica, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Vertica, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109925930","display_name":"Meichun Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meichun Hsu","raw_affiliation_strings":["HP Vertica, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Vertica, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088504528","display_name":"Indrajit Roy","orcid":"https://orcid.org/0000-0002-4766-2664"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Indrajit Roy","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2857,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86335393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1657","last_page":"1668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9925000071525574,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.9578989744186401},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8549444675445557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8177388310432434},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5897212028503418},{"id":"https://openalex.org/keywords/predictive-analytics","display_name":"Predictive analytics","score":0.5633218884468079},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5484868884086609},{"id":"https://openalex.org/keywords/open-database-connectivity","display_name":"Open Database Connectivity","score":0.5234729051589966},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5221555233001709},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4860265851020813},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46612122654914856},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43938225507736206},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3626363277435303},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1651034653186798},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0804007351398468}],"concepts":[{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.9578989744186401},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8549444675445557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177388310432434},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5897212028503418},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.5633218884468079},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5484868884086609},{"id":"https://openalex.org/C123327596","wikidata":"https://www.wikidata.org/wiki/Q212606","display_name":"Open Database Connectivity","level":5,"score":0.5234729051589966},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5221555233001709},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4860265851020813},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46612122654914856},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43938225507736206},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3626363277435303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1651034653186798},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0804007351398468},{"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/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"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/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.0},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2723372.2742789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2742789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W1973262089","https://openalex.org/W1976860187","https://openalex.org/W2006296837","https://openalex.org/W2011777324","https://openalex.org/W2013344760","https://openalex.org/W2013373704","https://openalex.org/W2044849727","https://openalex.org/W2066636486","https://openalex.org/W2068410942","https://openalex.org/W2131975293","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2397760010"],"related_works":["https://openalex.org/W2570647323","https://openalex.org/W2206805568","https://openalex.org/W2076942471","https://openalex.org/W2863268765","https://openalex.org/W3027285423","https://openalex.org/W2896245927","https://openalex.org/W4205879366","https://openalex.org/W1961101704","https://openalex.org/W4254129905","https://openalex.org/W2414447594"],"abstract_inverted_index":{"A":[0],"typical":[1],"predictive":[2],"analytics":[3],"workflow":[4,40],"will":[5],"pre-process":[6],"data":[7,14,46],"in":[8,27],"a":[9],"database,":[10],"transfer":[11],"the":[12,32],"resulting":[13],"to":[15,71,78],"an":[16],"external":[17],"statistical":[18],"tool":[19],"such":[20],"as":[21],"R,":[22,28],"create":[23],"machine":[24],"learning":[25],"models":[26,59,80],"and":[29,43],"then":[30],"apply":[31,79],"model":[33],"on":[34,55,60,81],"newly":[35,84],"arriving":[36,85],"data.":[37,86],"Today,":[38],"this":[39],"is":[41,68],"slow":[42],"cumbersome.":[44],"Extracting":[45],"from":[47],"databases,":[48],"using":[49],"ODBC":[50],"connectors,":[51],"can":[52],"take":[53],"hours":[54],"multi-gigabyte":[56],"datasets.":[57],"Building":[58],"single-threaded":[61],"R":[62,73],"does":[63],"not":[64],"scale.":[65],"Finally,":[66],"it":[67],"nearly":[69],"impossible":[70],"use":[72],"or":[74],"other":[75],"common":[76],"tools,":[77],"terabytes":[82],"of":[83]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}