{"id":"https://openalex.org/W4406248182","doi":"https://doi.org/10.1142/s0218213025400019","title":"SHAP as a Data Reduction Technique for Highly Imbalanced Big Data","display_name":"SHAP as a Data Reduction Technique for Highly Imbalanced Big Data","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4406248182","doi":"https://doi.org/10.1142/s0218213025400019"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213025400019","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213025400019","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047489766","display_name":"John Hancock","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John T. Hancock","raw_affiliation_strings":["College of Engineering and Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, Florida 33431, USA"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, Florida 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068409386","display_name":"Richard A. Bauder","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard A. Bauder","raw_affiliation_strings":["College of Engineering and Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, Florida 33431, USA"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, Florida 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089170562","display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["College of Engineering and Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, Florida 33431, USA"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, Florida 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047489766"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":null,"apc_paid":null,"fwci":0.699,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64183265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"04n05","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9132999777793884,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9132999777793884,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7058131694793701},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5960410237312317},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.47371000051498413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4345405101776123},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33104732632637024},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25045061111450195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058131694793701},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5960410237312317},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.47371000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4345405101776123},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33104732632637024},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25045061111450195},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213025400019","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213025400019","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1963632221","https://openalex.org/W2049633694","https://openalex.org/W2056132907","https://openalex.org/W2087046691","https://openalex.org/W2089468765","https://openalex.org/W2112796928","https://openalex.org/W2118324213","https://openalex.org/W2295598076","https://openalex.org/W2318802957","https://openalex.org/W2487898712","https://openalex.org/W2495589275","https://openalex.org/W2564754306","https://openalex.org/W2773235741","https://openalex.org/W2911964244","https://openalex.org/W2992495437","https://openalex.org/W3200552577","https://openalex.org/W4235730433","https://openalex.org/W4312628478","https://openalex.org/W4317040541","https://openalex.org/W4323240751","https://openalex.org/W4364361380","https://openalex.org/W4366308790","https://openalex.org/W4376129227","https://openalex.org/W4386274077","https://openalex.org/W4386274100","https://openalex.org/W4386274170","https://openalex.org/W4389989016"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2106145857","https://openalex.org/W2731626691","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822"],"abstract_inverted_index":{"Fraud":[0],"detection":[1,25,153],"through":[2,161],"the":[3,19,28,38,45,68,92,130,168,176],"classification":[4,82],"of":[5,14,30,47,70,173],"highly":[6,122],"imbalanced":[7,123],"Big":[8,149],"Data":[9],"is":[10,33,60,104],"an":[11,34,156],"exciting":[12],"area":[13],"Machine":[15,49],"Learning":[16,50],"research.":[17],"On":[18,37],"one":[20],"hand,":[21,40],"in":[22,112,148,171],"certain":[23],"fraud":[24,95,99,152],"application":[26,100],"domains,":[27],"use":[29,110],"One-Class":[31,62,81,115],"classifiers":[32],"overlooked":[35],"opportunity.":[36],"other":[39],"for":[41,52,80],"researchers":[42,108],"faced":[43],"with":[44,114,129,167],"task":[46],"building":[48],"models":[51,141],"identifying":[53],"fraud,":[54],"when":[55],"only":[56],"legitimate":[57],"transaction":[58],"data":[59,90,151,159],"available,":[61],"Classifiers":[63,116],"are":[64],"indispensable.":[65],"We":[66],"investigate":[67],"efficacy":[69],"SHapley":[71],"Additive":[72],"exPlanations":[73],"(SHAP)":[74],"as":[75],"a":[76],"feature":[77,119,162],"selection":[78,120,163],"technique":[79],"tasks.":[83],"In":[84],"this":[85],"study":[86],"we":[87],"utilize":[88],"authentic":[89],"from":[91],"Credit":[93],"Card":[94],"and":[96,125],"Medicare":[97,150],"insurance":[98],"domains.":[101],"Our":[102,146],"contribution":[103],"to":[105,117],"show":[106,154],"that":[107,133,155],"can":[109,164],"SHAP":[111],"conjunction":[113],"do":[118],"on":[121],"datasets,":[124],"then":[126],"build":[127],"models,":[128],"selected":[131],"features,":[132],"yield":[134],"performance":[135,170],"similar":[136],"to,":[137],"or":[138],"better":[139],"than,":[140],"built":[142],"using":[143],"all":[144],"features.":[145],"results":[147],"over":[157],"90%":[158],"reduction":[160],"nevertheless":[165],"coincide":[166],"best":[169],"terms":[172],"Area":[174],"under":[175],"Precision":[177],"Recall":[178],"Curve.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}