{"id":"https://openalex.org/W4404351599","doi":"https://doi.org/10.1145/3677052.3698616","title":"Can an unsupervised clustering algorithm reproduce a categorization system?","display_name":"Can an unsupervised clustering algorithm reproduce a categorization system?","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404351599","doi":"https://doi.org/10.1145/3677052.3698616"},"language":"en","primary_location":{"id":"doi:10.1145/3677052.3698616","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698616","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698616","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698616","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113549995","display_name":"N.P. Castellanos","orcid":null},"institutions":[{"id":"https://openalex.org/I55884533","display_name":"BlackRock (United States)","ror":"https://ror.org/031dc4703","country_code":"US","type":"company","lineage":["https://openalex.org/I55884533"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nathalia M Castellanos","raw_affiliation_strings":["BlackRock, Inc., United States"],"raw_orcid":"https://orcid.org/0009-0005-7471-4422","affiliations":[{"raw_affiliation_string":"BlackRock, Inc., United States","institution_ids":["https://openalex.org/I55884533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021022819","display_name":"Sebastian Frank","orcid":null},"institutions":[{"id":"https://openalex.org/I55884533","display_name":"BlackRock (United States)","ror":"https://ror.org/031dc4703","country_code":"US","type":"company","lineage":["https://openalex.org/I55884533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Frank","raw_affiliation_strings":["BlackRock, Inc., United States"],"raw_orcid":"https://orcid.org/0009-0009-5455-3851","affiliations":[{"raw_affiliation_string":"BlackRock, Inc., United States","institution_ids":["https://openalex.org/I55884533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008885741","display_name":"Dhruv Desai","orcid":"https://orcid.org/0009-0006-7728-0081"},"institutions":[{"id":"https://openalex.org/I55884533","display_name":"BlackRock (United States)","ror":"https://ror.org/031dc4703","country_code":"US","type":"company","lineage":["https://openalex.org/I55884533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Desai","raw_affiliation_strings":["BlackRock, Inc., United States"],"raw_orcid":"https://orcid.org/0009-0006-7728-0081","affiliations":[{"raw_affiliation_string":"BlackRock, Inc., United States","institution_ids":["https://openalex.org/I55884533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030132224","display_name":"Stefano Pasquali","orcid":"https://orcid.org/0009-0007-8005-3207"},"institutions":[{"id":"https://openalex.org/I55884533","display_name":"BlackRock (United States)","ror":"https://ror.org/031dc4703","country_code":"US","type":"company","lineage":["https://openalex.org/I55884533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefano Pasquali","raw_affiliation_strings":["BlackRock, Inc., United States"],"raw_orcid":"https://orcid.org/0009-0007-8005-3207","affiliations":[{"raw_affiliation_string":"BlackRock, Inc., United States","institution_ids":["https://openalex.org/I55884533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056701307","display_name":"Dhagash Mehta","orcid":"https://orcid.org/0000-0002-1040-9032"},"institutions":[{"id":"https://openalex.org/I55884533","display_name":"BlackRock (United States)","ror":"https://ror.org/031dc4703","country_code":"US","type":"company","lineage":["https://openalex.org/I55884533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhagash Mehta","raw_affiliation_strings":["BlackRock, Inc., United States"],"raw_orcid":"https://orcid.org/0000-0002-1040-9032","affiliations":[{"raw_affiliation_string":"BlackRock, Inc., United States","institution_ids":["https://openalex.org/I55884533"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113549995"],"corresponding_institution_ids":["https://openalex.org/I55884533"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1783096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976999759674072,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10320","display_name":"Neural Networks and Applications","score":0.9855999946594238,"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/computer-science","display_name":"Computer science","score":0.7741166353225708},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7563387155532837},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7090389728546143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5335133075714111},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.49392300844192505},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4590204656124115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45589733123779297},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4190892279148102},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.402538001537323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40027058124542236},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37397271394729614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741166353225708},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7563387155532837},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7090389728546143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5335133075714111},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.49392300844192505},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4590204656124115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45589733123779297},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4190892279148102},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.402538001537323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40027058124542236},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37397271394729614}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677052.3698616","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698616","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698616","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3677052.3698616","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698616","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698616","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404351599.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1939688770","https://openalex.org/W1987971958","https://openalex.org/W2030644393","https://openalex.org/W2037393175","https://openalex.org/W2039576845","https://openalex.org/W2051224630","https://openalex.org/W2071949631","https://openalex.org/W2085487226","https://openalex.org/W2090026055","https://openalex.org/W2162833336","https://openalex.org/W2396594725","https://openalex.org/W2468936963","https://openalex.org/W2587839772","https://openalex.org/W2968396469","https://openalex.org/W2993894543","https://openalex.org/W3047712904","https://openalex.org/W3086505308","https://openalex.org/W3121160015","https://openalex.org/W3121737315","https://openalex.org/W3196132318","https://openalex.org/W3201874838","https://openalex.org/W3209429958","https://openalex.org/W4213418104","https://openalex.org/W4235169531","https://openalex.org/W4306935468","https://openalex.org/W4312433903","https://openalex.org/W4383199656","https://openalex.org/W4388994243","https://openalex.org/W6723168715","https://openalex.org/W6839719062"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2622412490","https://openalex.org/W3140018618","https://openalex.org/W3161536855","https://openalex.org/W1970969031","https://openalex.org/W2049890817","https://openalex.org/W2182391068","https://openalex.org/W2607137685","https://openalex.org/W3009047669","https://openalex.org/W3111181422"],"abstract_inverted_index":{"Peer":[0],"analysis":[1],"is":[2,18,78,120],"a":[3,46,116,124],"critical":[4],"component":[5],"of":[6,85,95],"investment":[7],"management,":[8],"often":[9],"relying":[10],"on":[11,53],"expert-provided":[12],"categorization":[13,66],"systems.":[14],"These":[15],"systems\u2019":[16],"consistency":[17],"questioned":[19],"when":[20],"they":[21],"do":[22],"not":[23],"align":[24],"with":[25],"cohorts":[26],"from":[27],"unsupervised":[28,38,134],"clustering":[29,39,87,135],"algorithms":[30],"optimized":[31],"for":[32],"various":[33],"metrics.":[34],"We":[35,80,103],"investigate":[36],"whether":[37],"can":[40,136],"reproduce":[41,138],"ground":[42,75,100,140],"truth":[43,76,101,141],"classes":[44,77,142],"in":[45,90,112],"labeled":[47],"dataset,":[48,114],"showing":[49],"that":[50,72,106],"success":[51],"depends":[52],"feature":[54],"selection":[55],"and":[56,64,115],"the":[57,83,92,99,113,139],"chosen":[58],"distance":[59,118,128],"metric.":[60],"Using":[61],"toy":[62],"datasets":[63],"fund":[65],"as":[67,143],"real-world":[68],"examples":[69],"we":[70],"demonstrate":[71],"accurately":[73],"reproducing":[74],"challenging.":[79],"also":[81],"highlight":[82],"limitations":[84],"standard":[86],"evaluation":[88],"metrics":[89],"identifying":[91],"optimal":[93],"number":[94],"clusters":[96],"relative":[97],"to":[98],"classes.":[102],"then":[104,132],"show":[105],"if":[107],"appropriate":[108],"features":[109],"are":[110],"available":[111],"proper":[117],"metric":[119,129],"known":[121],"(e.g.,":[122],"using":[123],"supervised":[125],"Random":[126],"Forest-based":[127],"learning":[130],"method),":[131],"an":[133],"indeed":[137],"distinct":[144],"clusters.":[145]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
