{"id":"https://openalex.org/W4382467674","doi":"https://doi.org/10.1016/j.simpa.2023.100532","title":"Atlantic\u2014Automated data preprocessing framework for supervised machine learning","display_name":"Atlantic\u2014Automated data preprocessing framework for supervised machine learning","publication_year":2023,"publication_date":"2023-06-28","ids":{"openalex":"https://openalex.org/W4382467674","doi":"https://doi.org/10.1016/j.simpa.2023.100532"},"language":"en","primary_location":{"id":"doi:10.1016/j.simpa.2023.100532","doi":"https://doi.org/10.1016/j.simpa.2023.100532","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.simpa.2023.100532","pdf_url":"http://www.softwareimpacts.com/article/S2665963823000696/pdf","source":{"id":"https://openalex.org/S4210180398","display_name":"Software Impacts","issn_l":"2665-9638","issn":["2665-9638"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Impacts","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.softwareimpacts.com/article/S2665963823000696/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101435064","display_name":"Lu\u00eds Santos","orcid":"https://orcid.org/0000-0002-4121-1133","observed_orcids":["https://orcid.org/0000-0002-4121-1133"]},"institutions":[{"id":"https://openalex.org/I4405256586","display_name":"DTX Digital Transformation CoLAB","ror":"https://ror.org/04aykk734","country_code":"PT","type":"other","lineage":["https://openalex.org/I4405256586"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Lu\u00eds Santos","raw_affiliation_strings":["Digital Transfomation CoLAB, Guimar\u00e3es, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-4121-1133","affiliations":[{"raw_affiliation_string":"Digital Transfomation CoLAB, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4405256586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042734311","display_name":"Lu\u00eds Ferreira","orcid":"https://orcid.org/0000-0002-4790-5128","observed_orcids":["https://orcid.org/0000-0002-4790-5128"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu\u00eds Ferreira","raw_affiliation_strings":["Critical Techworks, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Critical Techworks, Porto, Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101435064"],"corresponding_institution_ids":["https://openalex.org/I4405256586"],"apc_list":{"value":260,"currency":"USD","value_usd":260},"apc_paid":{"value":260,"currency":"USD","value_usd":260},"fwci":0.6236,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.65919364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"17","issue":null,"first_page":"100532","last_page":"100532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9883000254631042,"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":0.9883000254631042,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.003599999938160181,"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/T11719","display_name":"Data Quality and Management","score":0.0010999999940395355,"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/data-preprocessing","display_name":"data preprocessing","score":0.6380000114440918},{"id":"https://openalex.org/keywords/automated-preprocessing-pipeline","display_name":"automated preprocessing pipeline","score":0.7179999947547913},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.9269999861717224},{"id":"https://openalex.org/keywords/python-library","display_name":"Python library","score":0.7179999947547913},{"id":"https://openalex.org/keywords/automatic-feature-selection","display_name":"automatic feature selection","score":0.8629999756813049},{"id":"https://openalex.org/keywords/categorical-encoding","display_name":"categorical encoding","score":0.9990000128746033},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.7300000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772688269615173},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7491929531097412},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6798862218856812},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6513791084289551},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6145252585411072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5863264799118042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5574578642845154},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5182280540466309},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5132851600646973},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49242934584617615},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.483573853969574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.13101443648338318},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1001516580581665}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.simpa.2023.100532","doi":"https://doi.org/10.1016/j.simpa.2023.100532","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.simpa.2023.100532","pdf_url":"http://www.softwareimpacts.com/article/S2665963823000696/pdf","source":{"id":"https://openalex.org/S4210180398","display_name":"Software Impacts","issn_l":"2665-9638","issn":["2665-9638"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Impacts","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.simpa.2023.100532","doi":"https://doi.org/10.1016/j.simpa.2023.100532","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.simpa.2023.100532","pdf_url":"http://www.softwareimpacts.com/article/S2665963823000696/pdf","source":{"id":"https://openalex.org/S4210180398","display_name":"Software Impacts","issn_l":"2665-9638","issn":["2665-9638"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Impacts","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382467674.pdf","grobid_xml":"https://content.openalex.org/works/W4382467674.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1821491182","https://openalex.org/W1961147827","https://openalex.org/W2099600742","https://openalex.org/W2547480331","https://openalex.org/W2584781382","https://openalex.org/W2791315675","https://openalex.org/W4200265911","https://openalex.org/W4246998055","https://openalex.org/W4285019205","https://openalex.org/W4312405752"],"related_works":["https://openalex.org/W6928764794","https://openalex.org/W4291910525","https://openalex.org/W4220866196","https://openalex.org/W4413361211","https://openalex.org/W7008147894","https://openalex.org/W7217475142","https://openalex.org/W4405480575","https://openalex.org/W7140116507","https://openalex.org/W4392308717","https://openalex.org/W4281565862"],"abstract_inverted_index":{"Atlantic":[0,20,52,69],"is":[1,70],"an":[2,57],"open-source":[3],"Python":[4],"package":[5,21],"designed":[6],"to":[7,43,48,71,85,94],"simplify":[8],"and":[9,37],"automate":[10],"data":[11,49],"preprocessing":[12,25,54,78],"for":[13,80],"supervised":[14],"ML":[15,91],"(Machine":[16],"Learning)":[17],"tasks.":[18],"The":[19,65],"integrates":[22],"multiple":[23],"customizable":[24],"mechanisms,":[26],"including":[27],"datetime":[28],"feature":[29,32],"engineering,":[30],"automated":[31,53],"selection,":[33],"categorical":[34],"encoding":[35],"techniques":[36],"null":[38],"imputation":[39],"methods.":[40],"In":[41],"order":[42],"provide":[44],"a":[45,81],"comprehensive":[46],"approach":[47],"processing":[50],"automation,":[51],"pipeline":[55],"follows":[56],"optimization":[58],"method":[59],"based":[60],"on":[61],"tree-based":[62],"models":[63,92],"ensembles.":[64],"main":[66],"goal":[67],"of":[68,77,89],"automatically":[72],"identify":[73],"the":[74,87],"best":[75],"combination":[76],"mechanisms":[79],"specific":[82],"dataset,":[83],"aiming":[84],"improve":[86],"performance":[88],"future":[90],"applied":[93],"that":[95],"data.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2023-06-29T00:00:00"}