{"id":"https://openalex.org/W7225833733","doi":"https://doi.org/10.1007/s42979-026-05421-7","title":"Controlled Synthesis of Imperfect Datasets for Machine Learning Education: A Variational Autoencoder, Wasserstein GAN, and Gaussian Mixture Model Framework with Domain-Aware Fraud and Error Injection","display_name":"Controlled Synthesis of Imperfect Datasets for Machine Learning Education: A Variational Autoencoder, Wasserstein GAN, and Gaussian Mixture Model Framework with Domain-Aware Fraud and Error Injection","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225833733","doi":"https://doi.org/10.1007/s42979-026-05421-7"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-026-05421-7","doi":"https://doi.org/10.1007/s42979-026-05421-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-026-05421-7","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20","russia-white-list-4","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s42979-026-05421-7","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017625768","display_name":"Khoa Phung","orcid":"https://orcid.org/0000-0002-9341-2033","observed_orcids":["https://orcid.org/0000-0002-9341-2033"]},"institutions":[{"id":"https://openalex.org/I178535277","display_name":"University of the West of England","ror":"https://ror.org/02nwg5t34","country_code":"GB","type":"education","lineage":["https://openalex.org/I178535277"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Khoa Phung","raw_affiliation_strings":["School of Computing and Creative Technologies, University of the West of England, Bristol, UK"],"raw_orcid":"https://orcid.org/0000-0002-9341-2033","affiliations":[{"raw_affiliation_string":"School of Computing and Creative Technologies, University of the West of England, Bristol, UK","institution_ids":["https://openalex.org/I178535277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5017625768"],"corresponding_institution_ids":["https://openalex.org/I178535277"],"apc_list":{"value":3190,"currency":"USD","value_usd":3190},"apc_paid":{"value":3190,"currency":"USD","value_usd":3190},"fwci":0.0,"has_fulltext":false,"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":"7","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.271699994802475,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.271699994802475,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.21860000491142273,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.09189999848604202,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6960999965667725},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6266000270843506},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5838000178337097},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5210999846458435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5202999711036682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993000030517578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43700000643730164},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3402000069618225},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C179024874","wikidata":"https://www.wikidata.org/wiki/Q5395728","display_name":"Errors-in-variables models","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C145097563","wikidata":"https://www.wikidata.org/wiki/Q1148747","display_name":"Payment","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42979-026-05421-7","doi":"https://doi.org/10.1007/s42979-026-05421-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-026-05421-7","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20","russia-white-list-4","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s42979-026-05421-7","doi":"https://doi.org/10.1007/s42979-026-05421-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-026-05421-7","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20","russia-white-list-4","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1959608418","https://openalex.org/W1993729533","https://openalex.org/W2049633694","https://openalex.org/W2061504941","https://openalex.org/W2070635017","https://openalex.org/W2100358124","https://openalex.org/W2102330235","https://openalex.org/W2110065044","https://openalex.org/W2115098571","https://openalex.org/W2115389369","https://openalex.org/W2130987150","https://openalex.org/W2158698691","https://openalex.org/W2163922914","https://openalex.org/W2190899134","https://openalex.org/W2210838531","https://openalex.org/W2217007515","https://openalex.org/W2229226246","https://openalex.org/W2296719434","https://openalex.org/W2480680997","https://openalex.org/W2481029616","https://openalex.org/W2565167788","https://openalex.org/W2779812635","https://openalex.org/W2911964244","https://openalex.org/W2964121744","https://openalex.org/W4235243453","https://openalex.org/W4254182148","https://openalex.org/W4387561528","https://openalex.org/W4401306886","https://openalex.org/W4403325819"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Machine":[1],"learning":[2],"and":[3,23,51,81,83,114,160,191,238,246,253,293,296,310,336,352,379,432,446],"data":[4,35,345],"science":[5],"education":[6],"overwhelmingly":[7],"relies":[8],"on":[9,240,289,307,330,470],"pre-cleaned,":[10],"statically":[11],"curated":[12],"benchmark":[13],"datasets":[14,26,67],"from":[15,43,181,373,458],"repositories":[16],"such":[17],"as":[18,129,363],"the":[19,31,125,200,208,214,230,241,264,281,303,321,324,333,356,359,374,415,439,447,459,489],"UCI":[20],"ML":[21],"Repository":[22],"Kaggle.":[24],"These":[25],"are":[27,450],"ill-suited":[28],"to":[29,69,124,207,332,381,419,452,464],"teaching":[30],"realities":[32],"of":[33,54,193,223,229,236,248,280,302,316,438,444],"production":[34],"pipelines,":[36],"which":[37,391],"invariably":[38],"contain":[39],"missing":[40],"values":[41],"arising":[42],"mixed":[44],"mechanisms,":[45],"domain-specific":[46],"typographic":[47],"errors,":[48],"format":[49],"inconsistencies,":[50],"embedded":[52],"fraud":[53,175,376],"varying":[55],"sophistication.":[56],"This":[57],"paper":[58],"presents":[59],"a":[60,95,107,118,164,168,219,226,255,285,297,314,403,422,430,486],"configurable":[61],"framework":[62,86,360],"for":[63,323,349,488],"generating":[64,364],"synthetic":[65],"imperfect":[66],"tailored":[68],"four":[70,201],"United":[71],"Kingdom":[72],"financial":[73],"domains:":[74],"banking":[75],"transactions,":[76],"mortgage":[77],"lending,":[78],"insurance":[79],"claims,":[80],"investment":[82],"trading.":[84],"The":[85],"offers":[87],"three":[88],"alternative":[89],"generators,":[90],"one":[91],"selected":[92],"per":[93],"request:":[94],"$$\\beta":[96,101,215,304],"$$":[97,102,216,305],"-Variational":[98],"Autoencoder":[99],"(":[100],"-VAE)":[103],"with":[104,110,117],"KL":[105],"annealing,":[106],"Wasserstein":[108],"GAN":[109],"Gradient":[111],"Penalty":[112],"(WGAN-GP)":[113],"their":[115,249],"hybrid,":[116],"Gaussian":[119,298],"Mixture":[120],"Model":[121],"(GMM)":[122],"fitted":[123,206,380],"VAE":[126],"latent":[127],"space":[128],"an":[130,144,393],"optional":[131],"prior,":[132],"all":[133],"implemented":[134],"entirely":[135],"in":[136,355,467,497],"pure":[137],"NumPy":[138],"so":[139,267,320,358],"that":[140,213,254,399,491],"every":[141,260],"operation":[142],"is":[143,300,327,337,361,484,495],"explicit":[145],"array":[146],"computation.":[147],"A":[148,173,276,370],"probabilistic":[149],"error":[150,171,312],"injection":[151,176,377,395,428],"layer":[152,177],"introduces":[153],"nine":[154],"distinct":[155],"corruption":[156],"types\u2014covering":[157],"MCAR,":[158],"MAR,":[159],"structural":[161],"errors\u2014allocated":[162],"via":[163],"Dirichlet":[165],"prior":[166],"over":[167],"user-specified":[169],"global":[170],"budget.":[172],"domain-aware":[174],"encodes":[178],"archetypes":[179,387],"drawn":[180],"UK":[182],"Finance,":[183],"Payment":[184],"Systems":[185],"Regulator,":[186],"Financial":[187],"Conduct":[188],"Authority":[189],"(FCA)":[190],"Association":[192],"British":[194],"Insurers":[195],"(ABI)":[196],"taxonomies.":[197],"Evaluation":[198],"across":[199],"domains,":[202],"against":[203,225,342],"external":[204],"baselines":[205],"same":[209,242,416],"training":[210],"splits,":[211],"shows":[212,346],"-VAE":[217,306],"attains":[218,284,383],"mean":[220],"Kolmogorov\u2013Smirnov":[221],"statistic":[222,287],"0.104":[224],"held-out":[227],"partition":[228],"rule-based":[231],"seed":[232,282,334],"corpus":[233,283,335],",":[234],"ahead":[235,301],"CTGAN":[237],"TVAE":[239],"target":[243],"at":[244,313,407],"1/34":[245],"1/9":[247],"respective":[250],"fitting":[251,318],"times,":[252],"structureless":[256],"independent-marginals":[257],"generator":[258],"matches":[259],"marginal":[261,268,291],"while":[262,421],"destroying":[263],"correlation":[265,294,311],"structure,":[266],"fidelity":[269,292,331],"alone":[270],"does":[271],"not":[272,328,338],"discriminate":[273],"between":[274],"generators.":[275],"zero-cost":[277],"smoothed":[278],"bootstrap":[279],"better":[286],"still":[288],"both":[290],"error,":[295],"copula":[299],"categorical":[308],"divergence":[309],"fifth":[315],"its":[317,408],"cost,":[319],"case":[322],"generative":[325],"stage":[326],"made":[329,339],"here.":[340],"Validation":[341],"real":[343],"record-level":[344],"close":[347],"agreement":[348],"bounded":[350],"quantities":[351],"substantial":[353],"disagreement":[354],"tails,":[357],"characterised":[362],"plausible":[365],"rather":[366],"than":[367],"realistic":[368],"records.":[369],"detector":[371,417],"transcribed":[372],"documented":[375],"ranges":[378],"nothing":[382],"AUROC":[384],"0.994":[385],"when":[386,456],"overwrite":[388],"records":[389,466],"outright,":[390],"motivates":[392],"overlap-controlled":[394],"scheme":[396],"introduced":[397],"here":[398],"makes":[400],"archetype":[401],"separability":[402],"declared":[404],"continuous":[405],"parameter;":[406],"default":[409,460],"expression":[410],"coefficient":[411],"$$\\lambda":[412],"=":[413],"0.25$$":[414],"falls":[418],"0.609,":[420],"trained":[423],"classifier":[424],"reaches":[425],"0.948.":[426],"Error":[427],"realises":[429],"stable":[431],"monotone":[433],"but":[434],"systematically":[435],"low":[436],"fraction":[437],"requested":[440],"rate,":[441],"averaging":[442],"0.596":[443],"it,":[445],"missingness":[448],"mechanisms":[449],"verified":[451],"be":[453,493],"correctly":[454],"instantiated":[455],"isolated":[457],"allocation.":[461],"Generation":[462],"scales":[463],"100,000":[465],"7.0":[468],"min":[469],"two":[471],"commodity":[472],"CPU":[473],"cores":[474],"without":[475],"GPU":[476],"acceleration.":[477],"No":[478],"evidence":[479],"involving":[480],"learners":[481],"or":[482],"instructors":[483],"presented;":[485],"protocol":[487],"evaluation":[490],"would":[492],"required":[494],"specified":[496],"full.":[498]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}