{"id":"https://openalex.org/W4407098113","doi":"https://doi.org/10.3390/a18020074","title":"Optimizing Apache Spark MLlib: Predictive Performance of Large-Scale Models for Big Data Analytics","display_name":"Optimizing Apache Spark MLlib: Predictive Performance of Large-Scale Models for Big Data Analytics","publication_year":2025,"publication_date":"2025-02-01","ids":{"openalex":"https://openalex.org/W4407098113","doi":"https://doi.org/10.3390/a18020074"},"language":"en","primary_location":{"id":"doi:10.3390/a18020074","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18020074","pdf_url":"https://www.mdpi.com/1999-4893/18/2/74/pdf?version=1739261997","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/18/2/74/pdf?version=1739261997","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019293826","display_name":"Leonidas Theodorakopoulos","orcid":"https://orcid.org/0000-0002-0891-6780"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Leonidas Theodorakopoulos","raw_affiliation_strings":["Department of Management Science and Technology, University of Patras, 26334 Patras, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Management Science and Technology, University of Patras, 26334 Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010990835","display_name":"Aristeidis Karras","orcid":"https://orcid.org/0000-0002-4632-6511"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Aristeidis Karras","raw_affiliation_strings":["Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026671559","display_name":"George A. Krimpas","orcid":"https://orcid.org/0009-0007-0008-547X"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George A. Krimpas","raw_affiliation_strings":["Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010990835"],"corresponding_institution_ids":["https://openalex.org/I174878644"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":47.2127,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.99775821,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"18","issue":"2","first_page":"74","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9668999910354614,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9668999910354614,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9477999806404114,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8128329515457153},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7982757091522217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6901301145553589},{"id":"https://openalex.org/keywords/predictive-analytics","display_name":"Predictive analytics","score":0.6155054569244385},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6153140664100647},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5551505088806152},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.412821888923645},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3281024992465973},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2990104556083679},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06782758235931396},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06561708450317383}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8128329515457153},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7982757091522217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901301145553589},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.6155054569244385},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6153140664100647},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5551505088806152},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.412821888923645},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3281024992465973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2990104556083679},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06782758235931396},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06561708450317383},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a18020074","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18020074","pdf_url":"https://www.mdpi.com/1999-4893/18/2/74/pdf?version=1739261997","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f54628fbc1004817a0e859e16730e9f3","is_oa":true,"landing_page_url":"https://doaj.org/article/f54628fbc1004817a0e859e16730e9f3","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 18, Iss 2, p 74 (2025)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/18/2/74/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a18020074","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pages: 74","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a18020074","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18020074","pdf_url":"https://www.mdpi.com/1999-4893/18/2/74/pdf?version=1739261997","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407098113.pdf","grobid_xml":"https://content.openalex.org/works/W4407098113.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2409628138","https://openalex.org/W2582789036","https://openalex.org/W2584830274","https://openalex.org/W2735828331","https://openalex.org/W2747362881","https://openalex.org/W2765546280","https://openalex.org/W2779309941","https://openalex.org/W2782959932","https://openalex.org/W2783557733","https://openalex.org/W2792955298","https://openalex.org/W2800147600","https://openalex.org/W2887718373","https://openalex.org/W2915282285","https://openalex.org/W2930448814","https://openalex.org/W2972515825","https://openalex.org/W2980656315","https://openalex.org/W3080570556","https://openalex.org/W3117549991","https://openalex.org/W3120147286","https://openalex.org/W3155420953","https://openalex.org/W3170664780","https://openalex.org/W3177290509","https://openalex.org/W3193985311","https://openalex.org/W3198116371","https://openalex.org/W3201479777","https://openalex.org/W4210727921","https://openalex.org/W4214895456","https://openalex.org/W4241679402","https://openalex.org/W4252719892","https://openalex.org/W4255917747","https://openalex.org/W4311120686","https://openalex.org/W4320737486","https://openalex.org/W4322731236","https://openalex.org/W4361251343","https://openalex.org/W4361750414","https://openalex.org/W4380143013","https://openalex.org/W4381886092","https://openalex.org/W4384828196","https://openalex.org/W4385478202","https://openalex.org/W4385603076","https://openalex.org/W4386714840","https://openalex.org/W4388628639","https://openalex.org/W4391094140","https://openalex.org/W4391230221","https://openalex.org/W4394911715","https://openalex.org/W4396698415","https://openalex.org/W4399564009","https://openalex.org/W4404044440","https://openalex.org/W6679267454"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2052370551","https://openalex.org/W2570647323","https://openalex.org/W3191926225","https://openalex.org/W3027285423","https://openalex.org/W2805665112","https://openalex.org/W4238120086"],"abstract_inverted_index":{"In":[0],"this":[1,132],"study,":[2],"we":[3],"analyze":[4],"the":[5,8,37,84,117,124,146],"performance":[6,126,141],"of":[7,39,87,119,127],"machine":[9],"learning":[10],"operators":[11],"in":[12,59,90,108,139],"Apache":[13,92],"Spark":[14,27,93],"MLlib":[15,94],"for":[16,73,148],"K-Means,":[17],"Random":[18],"Forest":[19],"Regression,":[20],"and":[21,42,78,104,122],"Word2Vec.":[22],"We":[23],"used":[24,48],"a":[25,70,105,152],"multi-node":[26],"cluster":[28],"along":[29],"with":[30],"collected":[31],"detailed":[32],"execution":[33],"metrics":[34],"computed":[35],"from":[36],"data":[38,46,129],"diverse":[40],"datasets":[41],"parameter":[43],"settings.":[44],"The":[45],"were":[47],"to":[49,56,100],"train":[50],"predictive":[51,65,140],"models":[52,89,112],"that":[53],"had":[54],"up":[55,99],"98%":[57],"accuracy":[58],"forecasting":[60],"performance.":[61],"By":[62],"building":[63],"actionable":[64],"models,":[66],"our":[67],"research":[68],"provides":[69],"unique":[71],"treatment":[72],"key":[74],"hyperparameter":[75],"tuning,":[76],"scalability,":[77],"real-time":[79,149],"resource":[80,102],"allocation":[81],"challenges.":[82],"Specifically,":[83],"practical":[85],"value":[86],"traditional":[88],"optimizing":[91],"workflows":[95],"was":[96],"shown,":[97],"achieving":[98],"30%":[101],"savings":[103],"25%":[106],"reduction":[107],"processing":[109],"time.":[110],"These":[111],"enable":[113],"system":[114],"optimization,":[115],"reduce":[116],"amount":[118],"computational":[120],"overheads,":[121],"boost":[123],"overall":[125],"big":[128],"applications.":[130],"Ultimately,":[131],"work":[133],"not":[134],"only":[135],"closes":[136],"significant":[137],"gaps":[138],"modeling,":[142],"but":[143],"also":[144],"paves":[145],"way":[147],"analytics":[150],"over":[151],"distributed":[153],"environment.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":18}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}