{"id":"https://openalex.org/W4410619272","doi":"https://doi.org/10.1186/s40537-025-01158-x","title":"FONDUE\u2014Fine-Tuned Optimization: Nurturing Data Usability & Efficiency","display_name":"FONDUE\u2014Fine-Tuned Optimization: Nurturing Data Usability & Efficiency","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4410619272","doi":"https://doi.org/10.1186/s40537-025-01158-x"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-025-01158-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01158-x","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01158-x","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01158-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052582753","display_name":"Valerie Restat","orcid":"https://orcid.org/0000-0002-5960-5886"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Valerie Restat","raw_affiliation_strings":["Chair of Databases and Information Systems, University of Hagen, Universit\u00e4tsstr. 1, 58097, Hagen, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Databases and Information Systems, University of Hagen, Universit\u00e4tsstr. 1, 58097, Hagen, Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114926779","display_name":"Indra Diestelk\u00e4mper","orcid":null},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Indra Diestelk\u00e4mper","raw_affiliation_strings":["Chair of Databases and Information Systems, University of Hagen, Universit\u00e4tsstr. 1, 58097, Hagen, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Databases and Information Systems, University of Hagen, Universit\u00e4tsstr. 1, 58097, Hagen, Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025927135","display_name":"Meike Klettke","orcid":"https://orcid.org/0000-0003-0551-8389"},"institutions":[{"id":"https://openalex.org/I120163777","display_name":"Regensburg University of Applied Sciences","ror":"https://ror.org/04b9vrm74","country_code":"DE","type":"education","lineage":["https://openalex.org/I120163777"]},{"id":"https://openalex.org/I60668342","display_name":"University of Regensburg","ror":"https://ror.org/01eezs655","country_code":"DE","type":"education","lineage":["https://openalex.org/I60668342"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meike Klettke","raw_affiliation_strings":["Chair for Data Engineering, University of Regensburg, Bajuwarenstra\u00dfe 4, 93053, Regensburg, Germany"],"affiliations":[{"raw_affiliation_string":"Chair for Data Engineering, University of Regensburg, Bajuwarenstra\u00dfe 4, 93053, Regensburg, Germany","institution_ids":["https://openalex.org/I60668342","https://openalex.org/I120163777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004678152","display_name":"Uta St\u00f6rl","orcid":"https://orcid.org/0000-0003-2771-142X"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Uta St\u00f6rl","raw_affiliation_strings":["Chair of Databases and Information Systems, University of Hagen, Universit\u00e4tsstr. 1, 58097, Hagen, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Databases and Information Systems, University of Hagen, Universit\u00e4tsstr. 1, 58097, Hagen, Germany","institution_ids":["https://openalex.org/I120691247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052582753"],"corresponding_institution_ids":["https://openalex.org/I120691247"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":1.4361,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8048028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9987999796867371,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9973000288009644,"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/usability","display_name":"Usability","score":0.826129138469696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986538410186768},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.5316135883331299},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4076617360115051},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37838709354400635}],"concepts":[{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.826129138469696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986538410186768},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.5316135883331299},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4076617360115051},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37838709354400635}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s40537-025-01158-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01158-x","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01158-x","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:doi:10.5283/epub.77126","is_oa":false,"landing_page_url":"https://epub.uni-regensburg.de/77126/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:2781da1d50fd494f90ea237af78831f5","is_oa":true,"landing_page_url":"https://doaj.org/article/2781da1d50fd494f90ea237af78831f5","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":"Journal of Big Data, Vol 12, Iss 1, Pp 1-27 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-025-01158-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01158-x","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01158-x","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410619272.pdf","grobid_xml":"https://content.openalex.org/works/W4410619272.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1917074954","https://openalex.org/W1939474812","https://openalex.org/W2015395371","https://openalex.org/W2027259333","https://openalex.org/W2044466855","https://openalex.org/W2078686663","https://openalex.org/W2110235052","https://openalex.org/W2131413649","https://openalex.org/W2151580670","https://openalex.org/W2185907055","https://openalex.org/W2421097601","https://openalex.org/W2485728689","https://openalex.org/W2544486974","https://openalex.org/W2805511080","https://openalex.org/W2889249015","https://openalex.org/W2918924753","https://openalex.org/W2929941791","https://openalex.org/W2948145720","https://openalex.org/W2966559104","https://openalex.org/W2971428651","https://openalex.org/W3035622304","https://openalex.org/W3045874819","https://openalex.org/W3105977086","https://openalex.org/W3110272195","https://openalex.org/W3111439114","https://openalex.org/W3173683037","https://openalex.org/W3176502563","https://openalex.org/W3217140273","https://openalex.org/W4200015620","https://openalex.org/W4221093169","https://openalex.org/W4231702991","https://openalex.org/W4240301789","https://openalex.org/W4244527061","https://openalex.org/W4281401329","https://openalex.org/W4293162521","https://openalex.org/W4302609958","https://openalex.org/W4312000335","https://openalex.org/W4381322923","https://openalex.org/W4385079049","https://openalex.org/W4385304812","https://openalex.org/W4386128230","https://openalex.org/W4387424085","https://openalex.org/W4399728706","https://openalex.org/W4404181119","https://openalex.org/W6758750208","https://openalex.org/W6979264032"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2429057255","https://openalex.org/W2187546663","https://openalex.org/W148745890","https://openalex.org/W4389670110","https://openalex.org/W2611942503","https://openalex.org/W4315621326","https://openalex.org/W2899790217"],"abstract_inverted_index":{"Abstract":[0],"To":[1],"provide":[2],"good":[3],"results":[4],"and":[5,31,86,94,138,191],"decisions":[6],"in":[7,70,132,146],"data-driven":[8],"systems,":[9],"data":[10,25,36,40,58,68,120,149,157,193,201],"quality":[11,41,59,202],"must":[12],"be":[13],"ensured":[14],"as":[15,83],"a":[16,55,176],"primary":[17],"consideration.":[18],"An":[19],"important":[20,197],"aspect":[21],"of":[22,54,73,104,111,135,148,162,180],"this":[23,47],"is":[24,43,154,186],"cleaning.":[26],"Although":[27],"many":[28,64],"different":[29,163],"algorithms":[30,122],"tools":[32],"already":[33],"exist":[34],"for":[35,170,199],"cleaning,":[37],"an":[38,92,155],"end-to-end":[39,57],"solution":[42],"still":[44],"needed.":[45],"In":[46,61],"paper,":[48],"we":[49,182],"present":[50,183],"FONDUE,":[51,181],"our":[52,76],"vision":[53],"well-founded":[56],"optimizer.":[60],"contrast":[62],"to":[63,101,188],"studies":[65],"that":[66],"consider":[67],"cleaning":[69,121,158],"the":[71,112,118,133,142,152],"context":[72],"machine":[74],"learning,":[75],"approach":[77],"focuses":[78],"on":[79,126],"various":[80],"scenarios,":[81],"such":[82],"when":[84],"preprocessing":[85],"downstream":[87],"analysis":[88],"are":[89,123,144,196],"separated.":[90],"As":[91,175],"adaptive":[93],"easily":[95],"extendable":[96],"framework,":[97],"FONDUE":[98],"operates":[99],"similarly":[100],"proven":[102],"methods":[103],"database":[105],"query":[106],"optimization.":[107],"Analogously,":[108],"it":[109],"consists":[110],"following":[113],"parts:":[114],"Rule-based":[115],"optimization,":[116,140],"where":[117,141],"appropriate":[119],"selected":[124],"based":[125],"use":[127],"case":[128],"constraints,":[129],"optimizer":[130],"hints":[131],"form":[134],"best":[136],"practices,":[137],"cost-based":[139],"costs":[143],"measured":[145],"terms":[147],"quality.":[150,194],"Accordingly,":[151],"result":[153],"optimized":[156],"pipeline.":[159],"The":[160],"choice":[161],"optimization":[164],"goals":[165],"enables":[166],"further":[167],"flexibility,":[168],"e.g.":[169],"environments":[171],"with":[172,203],"limited":[173],"resources.":[174],"first":[177],"building":[178],"block":[179],"CheDDaR,":[184],"which":[185],"used":[187],"detect":[189],"errors":[190],"measure":[192],"Both":[195],"tasks":[198],"improving":[200],"FONDUE.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-05-23T00:00:00"}