{"id":"https://openalex.org/W7225587609","doi":"https://doi.org/10.64388/ire1724784","title":"Agent Based Framework For Automated Data Cleaning And Validation","display_name":"Agent Based Framework For Automated Data Cleaning And Validation","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225587609","doi":"https://doi.org/10.64388/ire1724784"},"language":"en","primary_location":{"id":"doi:10.64388/ire1724784","doi":"https://doi.org/10.64388/ire1724784","is_oa":true,"landing_page_url":"https://doi.org/10.64388/ire1724784","pdf_url":"https://www.irejournals.com/formatedpaper/1724784.pdf","source":{"id":"https://openalex.org/S5407000720","display_name":"Iconic Research and Engineering Journals","issn_l":"2456-8880","issn":["2456-8880"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iconic Research and Engineering Journals","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.irejournals.com/formatedpaper/1724784.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161266496","display_name":"Gnanashri J","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gnanashri J","raw_affiliation_strings":["GSSS Institute of Engineering and Technology for Women"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSSS Institute of Engineering and Technology for Women","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161296185","display_name":"Manya M N","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manya M N","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161268143","display_name":"Sakshi C Patil","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I65674248","display_name":"Visvesvaraya Technological University","ror":"https://ror.org/00ha14p11","country_code":"IN","type":"education","lineage":["https://openalex.org/I65674248"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sakshi C Patil","raw_affiliation_strings":["Department of Artificial Intelligence and Data Science , GSSS Institute of Engineering and Technology for Women (affiliated to VTU) , Mysuru , Karnataka , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence and Data Science , GSSS Institute of Engineering and Technology for Women (affiliated to VTU) , Mysuru , Karnataka , India","institution_ids":["https://openalex.org/I65674248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161301655","display_name":"Likitha B","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Likitha B","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"5","first_page":"1736","last_page":"1750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.0,"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/automated-data-cleaning","display_name":"automated data cleaning","score":0.9459999799728394},{"id":"https://openalex.org/keywords/data-validation","display_name":"data validation","score":0.9110000133514404},{"id":"https://openalex.org/keywords/agent-based-framework","display_name":"agent-based framework","score":0.7900000214576721},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.8360000252723694},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.7620000243186951},{"id":"https://openalex.org/keywords/duplicate-records","display_name":"duplicate records","score":0.9509999752044678},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.8820000290870667},{"id":"https://openalex.org/keywords/schema-matching","display_name":"schema matching","score":0.9430000185966492},{"id":"https://openalex.org/keywords/data-merging","display_name":"data merging","score":0.8169999718666077},{"id":"https://openalex.org/keywords/data-quality-rules","display_name":"data quality rules","score":0.8209999799728394},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"human-in-the-loop","score":0.6499999761581421},{"id":"https://openalex.org/keywords/customer-data","display_name":"customer data","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210999727249146},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5949000120162964},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.375900000333786},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3095000088214874},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2644999921321869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64388/ire1724784","doi":"https://doi.org/10.64388/ire1724784","is_oa":true,"landing_page_url":"https://doi.org/10.64388/ire1724784","pdf_url":"https://www.irejournals.com/formatedpaper/1724784.pdf","source":{"id":"https://openalex.org/S5407000720","display_name":"Iconic Research and Engineering Journals","issn_l":"2456-8880","issn":["2456-8880"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iconic Research and Engineering Journals","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.64388/ire1724784","doi":"https://doi.org/10.64388/ire1724784","is_oa":true,"landing_page_url":"https://doi.org/10.64388/ire1724784","pdf_url":"https://www.irejournals.com/formatedpaper/1724784.pdf","source":{"id":"https://openalex.org/S5407000720","display_name":"Iconic Research and Engineering Journals","issn_l":"2456-8880","issn":["2456-8880"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iconic Research and Engineering Journals","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/W7225587609.pdf","grobid_xml":"https://content.openalex.org/works/W7225587609.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2591700809","https://openalex.org/W2941345940","https://openalex.org/W4409892338","https://openalex.org/W4416034974","https://openalex.org/W6929604448"],"related_works":["https://openalex.org/W7225571057","https://openalex.org/W2977781673","https://openalex.org/W7171557347","https://openalex.org/W7128423927","https://openalex.org/W2971148757","https://openalex.org/W2777991486","https://openalex.org/W7153853367","https://openalex.org/W2914585587","https://openalex.org/W7201906906","https://openalex.org/W7224738854"],"abstract_inverted_index":{"Real-world":[0],"datasets":[1,147],"can":[2,126],"contain":[3],"missing":[4,161],"values,":[5],"duplicate":[6,164],"records,":[7],"inconsistent":[8],"data,":[9],"outliers,":[10],"and":[11,18,42,48,52,68,82,138,163,206],"invalid":[12],"entries.":[13],"Manual":[14],"cleaning":[15,91,190],"is":[16],"time-consuming,":[17],"the":[19,56,97,113,124,130,167],"result":[20],"must":[21],"be":[22,127],"checked":[23],"to":[24,96,129,197],"determine":[25],"whether":[26],"it":[27],"satisfies":[28],"data-quality":[29],"requirements.":[30],"This":[31],"paper":[32],"presents":[33],"an":[34,207],"agent-based":[35],"framework":[36,142,195],"for":[37,99,133,215],"automated":[38],"data":[39,212],"cleaning,":[40,67],"validation,":[41],"merging":[43,145],"implemented":[44],"using":[45,75,148],"Python,":[46],"NumPy,":[47],"Pandas,":[49],"with":[50],"Flask":[51],"scikit-learn":[53],"used":[54,214],"in":[55,159],"prototype":[57,177],"application.":[58],"Different":[59],"agents":[60],"handle":[61],"schema":[62,149],"profiling,":[63],"issue":[64,125],"detection,":[65],"reasoning,":[66],"validation.":[69],"The":[70,108,141,194],"system":[71],"detects":[72],"candidate":[73],"problems":[74],"type":[76],"inference,":[77],"pattern":[78],"matching,":[79,81],"hash":[80],"IQR-based":[83],"outlier":[84],"detection.":[85],"A":[86],"Reasoning":[87],"Agent":[88,110],"proposes":[89],"possible":[90],"actions,":[92],"which":[93],"are":[94,106,213],"presented":[95],"user":[98,139],"approval":[100],"or":[101,192,217],"rejection":[102],"before":[103,211],"accepted":[104],"transformations":[105],"applied.":[107],"Validation":[109],"then":[111],"checks":[112],"output":[114,179],"against":[115],"configured":[116],"quality":[117],"rules.":[118],"If":[119],"validation":[120,168,209],"identifies":[121],"remaining":[122],"problems,":[123],"returned":[128],"reasoning":[131],"stage":[132],"a":[134,153,157,182],"further":[135],"proposed":[136],"correction":[137],"decision.":[140],"also":[143],"supports":[144],"two":[146],"matching.":[150],"Screenshots":[151],"from":[152],"customer-data":[154],"demonstration":[155],"show":[156],"reduction":[158],"reported":[160],"values":[162],"rows,":[165],"while":[166,202],"dashboard":[169],"still":[170],"reports":[171],"failed":[172],"checks.":[173],"These":[174],"observations":[175],"describe":[176],"interface":[178],"rather":[180],"than":[181],"controlled":[183],"benchmark;":[184],"they":[185],"do":[186],"not":[187],"establish":[188],"general":[189],"accuracy":[191],"performance.":[193],"aims":[196],"reduce":[198],"repetitive":[199],"manual":[200],"work":[201],"retaining":[203],"human":[204],"oversight":[205],"explicit":[208],"step":[210],"analysis":[216],"machine":[218],"learning.":[219]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-09T00:00:00"}