{"id":"https://openalex.org/W4205695144","doi":"https://doi.org/10.1109/bigdata52589.2021.9671865","title":"Implementing Efficient and Scalable In-Database Linear Regression in SQL","display_name":"Implementing Efficient and Scalable In-Database Linear Regression in SQL","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205695144","doi":"https://doi.org/10.1109/bigdata52589.2021.9671865"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671865","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big 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/A5055333931","display_name":"Patrick Giesser","orcid":null},"institutions":[{"id":"https://openalex.org/I81007117","display_name":"Lucerne University of Applied Sciences and Arts","ror":"https://ror.org/04nd0xd48","country_code":"CH","type":"education","lineage":["https://openalex.org/I81007117"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Patrick Giesser","raw_affiliation_strings":["Informatik, Hochschule Luzern, Rotkreuz, Switzerland"],"affiliations":[{"raw_affiliation_string":"Informatik, Hochschule Luzern, Rotkreuz, Switzerland","institution_ids":["https://openalex.org/I81007117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053261091","display_name":"Gabriel Stechschulte","orcid":null},"institutions":[{"id":"https://openalex.org/I81007117","display_name":"Lucerne University of Applied Sciences and Arts","ror":"https://ror.org/04nd0xd48","country_code":"CH","type":"education","lineage":["https://openalex.org/I81007117"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gabriel Stechschulte","raw_affiliation_strings":["Wirtschaft, Hochschule Luzern, Lucerne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Wirtschaft, Hochschule Luzern, Lucerne, Switzerland","institution_ids":["https://openalex.org/I81007117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026155181","display_name":"Anna da Costa Vaz","orcid":null},"institutions":[{"id":"https://openalex.org/I81007117","display_name":"Lucerne University of Applied Sciences and Arts","ror":"https://ror.org/04nd0xd48","country_code":"CH","type":"education","lineage":["https://openalex.org/I81007117"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anna da Costa Vaz","raw_affiliation_strings":["Informatik, Hochschule Luzern, Rotkreuz, Switzerland"],"affiliations":[{"raw_affiliation_string":"Informatik, Hochschule Luzern, Rotkreuz, Switzerland","institution_ids":["https://openalex.org/I81007117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053940401","display_name":"M. Kaufmann","orcid":"https://orcid.org/0000-0003-1437-0996"},"institutions":[{"id":"https://openalex.org/I81007117","display_name":"Lucerne University of Applied Sciences and Arts","ror":"https://ror.org/04nd0xd48","country_code":"CH","type":"education","lineage":["https://openalex.org/I81007117"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michael Kaufmann","raw_affiliation_strings":["Informatik, Hochschule Luzern, Rotkreuz, Switzerland"],"affiliations":[{"raw_affiliation_string":"Informatik, Hochschule Luzern, Rotkreuz, Switzerland","institution_ids":["https://openalex.org/I81007117"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055333931"],"corresponding_institution_ids":["https://openalex.org/I81007117"],"apc_list":null,"apc_paid":null,"fwci":0.6188,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57312546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5125","last_page":"5132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9973000288009644,"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/T11719","display_name":"Data Quality and Management","score":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8405711650848389},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6774846315383911},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6474153995513916},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5554020404815674},{"id":"https://openalex.org/keywords/relational-database-management-system","display_name":"Relational database management system","score":0.5093528032302856},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45573410391807556},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4084802269935608},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.381838858127594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3513897657394409}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405711650848389},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6774846315383911},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6474153995513916},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5554020404815674},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.5093528032302856},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45573410391807556},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4084802269935608},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.381838858127594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3513897657394409}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671865","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1993892970","https://openalex.org/W2032840619","https://openalex.org/W2044849727","https://openalex.org/W2049713645","https://openalex.org/W2081643791","https://openalex.org/W2108751703","https://openalex.org/W2125547396","https://openalex.org/W2186081484","https://openalex.org/W2206925937","https://openalex.org/W2612139288","https://openalex.org/W2747149925","https://openalex.org/W2778067733","https://openalex.org/W2955512557","https://openalex.org/W2970977077","https://openalex.org/W2971169561","https://openalex.org/W3002707609","https://openalex.org/W3007024586","https://openalex.org/W3143318632","https://openalex.org/W4242109409","https://openalex.org/W6743154609","https://openalex.org/W6746780038","https://openalex.org/W6773642074","https://openalex.org/W6792670178"],"related_works":["https://openalex.org/W1982455124","https://openalex.org/W4385585331","https://openalex.org/W2505630977","https://openalex.org/W2383709723","https://openalex.org/W1497653608","https://openalex.org/W2015932315","https://openalex.org/W2573939812","https://openalex.org/W1575529579","https://openalex.org/W2545844851","https://openalex.org/W3022423983"],"abstract_inverted_index":{"Relational":[0],"database":[1,40],"management":[2],"systems":[3],"not":[4,45],"only":[5],"support":[6],"larger-than-memory":[7],"data":[8,21,31,43,56,245],"processing":[9,57,116,241],"and":[10,24,50,80,87,166,196],"very":[11],"advanced":[12],"query":[13],"optimization,":[14],"but":[15],"also":[16],"offer":[17],"the":[18,42,74,83,98,106,115,118,121,124,133,141,145,198,208,213],"benefits":[19],"of":[20,114,123,126,135,200,242,251],"security,":[22],"privacy,":[23],"consistency.":[25],"When":[26],"machine":[27,252],"learning":[28,253],"on":[29,36],"large":[30],"sets":[32,246],"is":[33,130,138,202,215,235],"processed":[34],"directly":[35,81,104],"an":[37,169,228],"existing":[38,170],"SQL":[39,69,109,142,234],"server,":[41],"does":[44],"need":[46],"to":[47,52,132,144,148,168],"be":[48,77,149,259],"exported":[49],"transferred":[51,139],"a":[53,64,222,236,248],"separate":[54],"big":[55],"platform.":[58],"To":[59],"achieve":[60],"this,":[61],"we":[62],"implement":[63],"linear":[65,94],"regression":[66,95,183],"algorithm":[67],"using":[68,97,108],"code":[70,110],"generation":[71],"such":[72,265],"that":[73,177,233,257],"computation":[75,214],"can":[76,258],"performed":[78],"server-side":[79],"in":[82,91,105,117],"RDBMs.":[84],"Our":[85],"method":[86,103],"its":[88],"implementation,":[89],"programmed":[90],"Python,":[92],"solves":[93,181],"(LR)":[96],"ordinary":[99],"least":[100],"squares":[101],"(OLS)":[102],"RDBMS":[107],"generation,":[111],"leaving":[112],"most":[113],"database.":[119],"Only":[120],"matrix":[122],"system":[125],"equations,":[127],"whose":[128],"size":[129],"equal":[131],"number":[134,199],"variables":[136],"squared,":[137],"from":[140],"server":[143],"Python":[146,171],"client":[147],"solved":[150,261],"for":[151,188,239],"OLS":[152,182,267],"regression.":[153,268],"For":[154],"evaluation":[155],"purposes,":[156],"our":[157,178,219],"LR":[158],"implementation":[159,179,220],"was":[160],"tested":[161],"with":[162,190,247,262],"artificially":[163],"generated":[164],"datasets":[165,189],"compared":[167],"library":[172],"(Scikit":[173],"Learn).":[174],"We":[175,231],"found":[176],"consistently":[180],"faster":[184],"than":[185,192,204,217],"Scikit":[186,226],"Learn":[187],"more":[191],"10,000":[193],"input":[194],"rows,":[195],"if":[197],"columns":[201],"less":[203],"64.":[205],"Moreover,":[206],"under":[207],"same":[209],"test":[210],"conditions":[211],"where":[212],"larger":[216],"memory,":[218],"showed":[221],"fast":[223],"result,":[224],"while":[225],"returned":[227],"out-of-memory":[229],"error.":[230],"conclude":[232],"promising":[237],"tool":[238],"in-database":[240],"large-volume,":[243],"low-dimensional":[244],"particular":[249],"class":[250],"algorithms,":[254],"namely":[255],"those":[256],"efficiently":[260],"map-reduce":[263],"queries":[264],"as":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}