{"id":"https://openalex.org/W7224619450","doi":"https://doi.org/10.66592/nfw294bd","title":"Automated Data-Quality Assessment and Intelligent Feature Engineering for Large-Scale Predictive Analytics","display_name":"Automated Data-Quality Assessment and Intelligent Feature Engineering for Large-Scale Predictive Analytics","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224619450","doi":"https://doi.org/10.66592/nfw294bd"},"language":"en","primary_location":{"id":"pmh:oai:ojs2.jistm.info:article/61","doi":"https://doi.org/10.66592/nfw294bd","is_oa":true,"landing_page_url":"https://jistm.info/index.php/jistm/article/view/61","pdf_url":"https://jistm.info/index.php/jistm/article/download/61/52","source":{"id":"https://openalex.org/S7407065220","display_name":"Journal of Integrated Science Technology and Management","issn_l":"3135-2456","issn":["3135-2456"],"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":"3135-2456","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://jistm.info/index.php/jistm/article/download/61/52","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160096736","display_name":"Anvar Tursunov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405254457","display_name":"Termez University of Economics and Service","ror":"https://ror.org/01tts0094","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405254457"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Tursunov, Anvar","raw_affiliation_strings":["Department of History, Termez University of Economics and Service, Termez, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of History, Termez University of Economics and Service, Termez, Uzbekistan","institution_ids":["https://openalex.org/I4405254457"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160149273","display_name":"Mohd Asif Khan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Mohd Asif","raw_affiliation_strings":["Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Researcher","institution_ids":[]}]}],"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":0.88645776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9653000235557556,"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":0.9653000235557556,"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":0.028200000524520874,"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":0.0017999999690800905,"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-quality-assessment","display_name":"data quality assessment","score":0.7720000147819519},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"feature engineering","score":0.7710000276565552},{"id":"https://openalex.org/keywords/predictive-analytics","display_name":"predictive analytics","score":0.7680000066757202},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.9210000038146973},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.7139999866485596},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.8769999742507935},{"id":"https://openalex.org/keywords/feature-stability","display_name":"feature stability","score":0.6019999980926514},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"distributed computing","score":0.5360000133514404},{"id":"https://openalex.org/keywords/experiment-tracking","display_name":"experiment tracking","score":0.7620000243186951},{"id":"https://openalex.org/keywords/model-reliability","display_name":"model reliability","score":0.6359999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470999956130981},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6996999979019165},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6259999871253967},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5924999713897705},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4893999993801117},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.45489999651908875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45210000872612},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C56397880","wikidata":"https://www.wikidata.org/wiki/Q6044094","display_name":"Intelligent decision support system","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs2.jistm.info:article/61","doi":"https://doi.org/10.66592/nfw294bd","is_oa":true,"landing_page_url":"https://jistm.info/index.php/jistm/article/view/61","pdf_url":"https://jistm.info/index.php/jistm/article/download/61/52","source":{"id":"https://openalex.org/S7407065220","display_name":"Journal of Integrated Science Technology and Management","issn_l":"3135-2456","issn":["3135-2456"],"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":"3135-2456","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:ojs2.jistm.info:article/61","doi":"https://doi.org/10.66592/nfw294bd","is_oa":true,"landing_page_url":"https://jistm.info/index.php/jistm/article/view/61","pdf_url":"https://jistm.info/index.php/jistm/article/download/61/52","source":{"id":"https://openalex.org/S7407065220","display_name":"Journal of Integrated Science Technology and Management","issn_l":"3135-2456","issn":["3135-2456"],"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":"3135-2456","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224619450.pdf","grobid_xml":"https://content.openalex.org/works/W7224619450.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7155402961","https://openalex.org/W4394936927","https://openalex.org/W4405659685","https://openalex.org/W7213555506","https://openalex.org/W7165689346","https://openalex.org/W7201845485","https://openalex.org/W7222898502","https://openalex.org/W7171539230","https://openalex.org/W962621462","https://openalex.org/W7155167785"],"abstract_inverted_index":{"Reliable":[0],"predictive":[1,20,78],"analytics":[2],"depends":[3],"not":[4,126],"only":[5],"on":[6,14,150],"the":[7,15],"capacity":[8],"of":[9,22],"learning":[10],"algorithms":[11],"but":[12],"also":[13],"quality,":[16],"semantic":[17],"consistency,":[18,52],"and":[19,54,62,66,84,95,102,118,143],"usefulness":[21],"input":[23],"data.":[24],"This":[25],"paper":[26],"develops":[27],"a":[28,104],"conceptual,":[29],"modular":[30],"framework":[31,130],"that":[32,135],"combines":[33],"automated":[34],"data-quality":[35,137],"assessment":[36],"with":[37],"intelligent":[38],"feature":[39,82],"engineering":[40],"for":[41,90,147],"large-scale":[42],"tabular":[43],"analytics.":[44],"The":[45,129],"proposed":[46],"pipeline":[47,111],"profiles":[48],"completeness,":[49],"validity,":[50],"uniqueness,":[51],"timeliness,":[53],"distributional":[55],"stability;":[56],"applies":[57],"risk-aware":[58],"remediation;":[59],"constructs":[60],"statistically":[61],"semantically":[63],"meaningful":[64],"features;":[65],"uses":[67],"leakage-safe":[68],"validation":[69],"to":[70,139],"select":[71],"transformations.":[72],"A":[73],"multi-objective":[74],"optimization":[75],"formulation":[76],"balances":[77],"utility,":[79],"computational":[80],"cost,":[81],"stability,":[83],"quality":[85],"risk.":[86],"An":[87],"implementation":[88],"protocol":[89],"distributed":[91],"processing,":[92],"experiment":[93],"tracking,":[94],"monitoring":[96],"is":[97],"specified.":[98],"To":[99],"demonstrate":[100],"reporting":[101],"interpretation,":[103],"transparent":[105],"illustrative":[106],"numerical":[107],"scenario":[108],"compares":[109],"four":[110],"configurations":[112],"across":[113],"accuracy,":[114],"F1":[115],"score,":[116],"AUROC,":[117],"processing":[119],"time.":[120],"These":[121],"figures":[122],"are":[123],"hypothetical":[124],"examples,":[125],"empirical":[127],"findings.":[128],"contributes":[131],"an":[132],"auditable":[133],"design":[134],"links":[136],"decisions":[138],"downstream":[140],"model":[141],"reliability":[142],"provides":[144],"testable":[145],"hypotheses":[146],"future":[148],"benchmarking":[149],"real":[151],"datasets.":[152]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}
