{"id":"https://openalex.org/W4406458786","doi":"https://doi.org/10.1109/bigdata62323.2024.10825671","title":"Integrating categorical and continuous data in a cluster-then-classify methodology for predicting undergraduate student success","display_name":"Integrating categorical and continuous data in a cluster-then-classify methodology for predicting undergraduate student success","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458786","doi":"https://doi.org/10.1109/bigdata62323.2024.10825671"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-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/A5015251069","display_name":"John Fields","orcid":"https://orcid.org/0000-0001-5153-0376"},"institutions":[{"id":"https://openalex.org/I102461120","display_name":"Marquette University","ror":"https://ror.org/04gr4te78","country_code":"US","type":"education","lineage":["https://openalex.org/I102461120"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Fields","raw_affiliation_strings":["Marquette University,Computer Science,Milwaukee,USA"],"affiliations":[{"raw_affiliation_string":"Marquette University,Computer Science,Milwaukee,USA","institution_ids":["https://openalex.org/I102461120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045174316","display_name":"Kevin Chovanec","orcid":"https://orcid.org/0009-0005-8869-9083"},"institutions":[{"id":"https://openalex.org/I102461120","display_name":"Marquette University","ror":"https://ror.org/04gr4te78","country_code":"US","type":"education","lineage":["https://openalex.org/I102461120"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Chovanec","raw_affiliation_strings":["Marquette University,Computer Science,Milwaukee,USA"],"affiliations":[{"raw_affiliation_string":"Marquette University,Computer Science,Milwaukee,USA","institution_ids":["https://openalex.org/I102461120"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031689008","display_name":"Praveen Madiraju","orcid":"https://orcid.org/0009-0006-9737-9601"},"institutions":[{"id":"https://openalex.org/I102461120","display_name":"Marquette University","ror":"https://ror.org/04gr4te78","country_code":"US","type":"education","lineage":["https://openalex.org/I102461120"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Praveen Madiraju","raw_affiliation_strings":["Marquette University,Computer Science,Milwaukee,USA"],"affiliations":[{"raw_affiliation_string":"Marquette University,Computer Science,Milwaukee,USA","institution_ids":["https://openalex.org/I102461120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015251069"],"corresponding_institution_ids":["https://openalex.org/I102461120"],"apc_list":null,"apc_paid":null,"fwci":0.8659,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.834813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8118","last_page":"8126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11122","display_name":"Online Learning and Analytics","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9830999970436096,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9607999920845032,"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":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.8920795321464539},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6453069448471069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6341555118560791},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4723442792892456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45386409759521484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3374779224395752}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8920795321464539},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6453069448471069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6341555118560791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4723442792892456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45386409759521484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3374779224395752},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W587621729","https://openalex.org/W1523179845","https://openalex.org/W1906645695","https://openalex.org/W1970881937","https://openalex.org/W2019933549","https://openalex.org/W2074724594","https://openalex.org/W2079259032","https://openalex.org/W2091297208","https://openalex.org/W2148143831","https://openalex.org/W2607469528","https://openalex.org/W2613905280","https://openalex.org/W2789293848","https://openalex.org/W2800292742","https://openalex.org/W2885000341","https://openalex.org/W2915650894","https://openalex.org/W2975743880","https://openalex.org/W3069935958","https://openalex.org/W3108414243","https://openalex.org/W3112381148","https://openalex.org/W3166077024","https://openalex.org/W3192298118","https://openalex.org/W4205515909","https://openalex.org/W4206491718","https://openalex.org/W4237416912","https://openalex.org/W4248650494","https://openalex.org/W4290044378","https://openalex.org/W4294085681","https://openalex.org/W4313289095","https://openalex.org/W4366169553","https://openalex.org/W4387024961","https://openalex.org/W4390590855","https://openalex.org/W4391093817","https://openalex.org/W4391402561","https://openalex.org/W4399335804","https://openalex.org/W4400485150","https://openalex.org/W6617264716","https://openalex.org/W6631445417","https://openalex.org/W6778271016","https://openalex.org/W6787394551","https://openalex.org/W6800132622"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Student":[0],"retention":[1],"in":[2,41,154,167],"higher":[3,155],"education":[4],"remains":[5],"a":[6,16,36,75,82,140,179],"significant":[7],"challenge":[8],"despite":[9],"decades":[10],"of":[11,93,143,203],"research.":[12],"This":[13,112],"study":[14],"introduces":[15],"novel":[17],"cluster-label-classify":[18],"methodology":[19,131],"to":[20,51,95,119,138,196],"predict":[21],"at-risk":[22,128],"students":[23,54,100,105],"and":[24,62,70,86,101,122,135,171],"identify":[25],"common":[26],"characteristics":[27],"among":[28],"those":[29],"who":[30],"drop":[31],"out.":[32],"Using":[33],"data":[34],"from":[35],"small":[37],"private":[38],"Midwestern":[39],"university":[40],"the":[42,48,71,168,201],"United":[43],"States,":[44],"we":[45,80],"first":[46],"applied":[47],"K-Prototypes":[49],"algorithm":[50],"cluster":[52],"non-retained":[53,99],"into":[55,150],"five":[56],"groups":[57],"based":[58],"on":[59,181],"both":[60],"numeric":[61],"categorical":[63],"variables.":[64],"We":[65],"then":[66],"labeled":[67],"these":[68,193],"clusters":[69],"retained":[72,104],"students,":[73],"creating":[74],"multi-class":[76],"classification":[77],"problem.":[78],"Finally,":[79,178],"used":[81],"Gradient":[83],"Boosting":[84],"Classifier":[85],"XGBoost":[87],"for":[88,97,103,115,127,174,190],"classification,":[89],"achieving":[90],"F1":[91],"scores":[92],"0.82":[94],"0.89":[96],"predicting":[98],"0.96":[102],"after":[106],"addressing":[107],"class":[108],"imbalance":[109],"with":[110],"SMOTE.":[111],"approach":[113],"allows":[114],"customized":[116],"labeling":[117],"specific":[118],"each":[120],"institution":[121],"enables":[123],"more":[124],"targeted":[125],"interventions":[126],"students.":[129],"Our":[130],"combines":[132],"demographic,":[133],"academic,":[134],"socioeconomic":[136],"factors":[137],"provide":[139],"comprehensive":[141],"view":[142],"student":[144,176,204],"retention,":[145],"potentially":[146],"offering":[147],"new":[148],"insights":[149],"this":[151],"longstanding":[152],"issue":[153],"education.":[156],"The":[157],"paper":[158],"also":[159],"discusses":[160],"algorithmic":[161],"bias,":[162],"examining":[163],"potential":[164],"fairness":[165],"issues":[166],"predictive":[169],"models":[170],"their":[172],"implications":[173],"different":[175],"populations.":[177],"discussion":[180],"Privacy":[182],"Preserving":[183],"Machine":[184],"Learning":[185],"(PPML)":[186],"provides":[187],"future":[188],"strategies":[189],"testing":[191],"how":[192],"technologies":[194],"generalize":[195],"other":[197],"institutions":[198],"while":[199],"enhancing":[200],"privacy":[202],"data.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}