{"id":"https://openalex.org/W2583353385","doi":"https://doi.org/10.1109/bigdata.2016.7841069","title":"Automatic classification of securities using hierarchical clustering of the 10-Ks","display_name":"Automatic classification of securities using hierarchical clustering of the 10-Ks","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583353385","doi":"https://doi.org/10.1109/bigdata.2016.7841069","mag":"2583353385"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7841069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/A5102324662","display_name":"Hoseong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hoseong Yang","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358242","display_name":"Hye Jin Lee","orcid":"https://orcid.org/0000-0002-6586-8447"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hye Jin Lee","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017305201","display_name":"Sungzoon Cho","orcid":"https://orcid.org/0000-0002-1695-1973"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungzoon Cho","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055161485","display_name":"Cho Eugene","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugene Cho","raw_affiliation_strings":["Annandale, VA, USA"],"affiliations":[{"raw_affiliation_string":"Annandale, VA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102324662"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.7953,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8783872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3936","last_page":"3943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10081","display_name":"Auditing, Earnings Management, Governance","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10047","display_name":"Financial Markets and Investment Strategies","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6998226642608643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6716055870056152},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5655694007873535},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5233566164970398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4376477003097534},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"Business intelligence","score":0.41330623626708984},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41084814071655273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37474891543388367}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6998226642608643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6716055870056152},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5655694007873535},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5233566164970398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4376477003097534},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.41330623626708984},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41084814071655273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37474891543388367}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7841069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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":24,"referenced_works":["https://openalex.org/W145476170","https://openalex.org/W2016381774","https://openalex.org/W2018381052","https://openalex.org/W2034084704","https://openalex.org/W2040198418","https://openalex.org/W2117130368","https://openalex.org/W2131744502","https://openalex.org/W2153579005","https://openalex.org/W2250753706","https://openalex.org/W2251939518","https://openalex.org/W2294675754","https://openalex.org/W2882319491","https://openalex.org/W2998704965","https://openalex.org/W3121243729","https://openalex.org/W3124462827","https://openalex.org/W3124806143","https://openalex.org/W3125302645","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W6605963037","https://openalex.org/W6679775712","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6691459498"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4247136043","https://openalex.org/W1986582023","https://openalex.org/W2883749686","https://openalex.org/W2966829450","https://openalex.org/W4315864862"],"abstract_inverted_index":{"Industry":[0,71],"classification":[1,14,40,67],"has":[2],"been":[3,18],"rigorously":[4],"utilized":[5],"in":[6,97,103,133,147,171],"academic":[7],"research":[8,135],"and":[9,20,30,52,113,145,151,169,179],"business":[10,91],"analytics.":[11],"The":[12],"existing":[13,39],"schemes,":[15],"however,":[16],"have":[17],"constructed":[19],"maintained":[21],"manually":[22],"by":[23],"domain":[24],"experts,":[25],"which":[26,98],"require":[27],"exhaustive":[28],"time":[29],"human":[31],"effort":[32],"while":[33],"vulnerable":[34],"to":[35,59,119],"subjectivity.":[36],"Hence,":[37],"the":[38,46,50,53,81,85,90,94,156],"systems":[41],"do":[42],"not":[43],"properly":[44],"reflect":[45],"fast-changing":[47],"trends":[48],"of":[49,93,149,159],"firms":[51,99],"capital":[54],"market.":[55],"As":[56],"a":[57,65,104],"remedy":[58],"such":[60],"shortcomings,":[61],"this":[62],"paper":[63],"proposes":[64],"new":[66],"scheme,":[68],"Business":[69],"Text":[70],"Classification":[72],"(BTIC),":[73],"namely,":[74],"that":[75,137,165],"automatically":[76],"clusters":[77],"securities":[78,121],"based":[79],"on":[80],"textual":[82],"information":[83],"from":[84],"corporate":[86],"disclosures.":[87],"BTIC":[88,123,138,166],"exploits":[89],"section":[92],"Form":[95],"10-Ks,":[96],"provide":[100],"their":[101],"self-identities":[102],"rich":[105],"context.":[106],"We":[107],"employ":[108],"doc2vec":[109],"for":[110,155],"document":[111],"embedding":[112],"apply":[114],"Ward's":[115],"hierarchical":[116],"clustering":[117,177],"method":[118],"categorize":[120],"into":[122],"groups.":[124],"Evaluation":[125],"results":[126],"using":[127],"12":[128],"financial":[129,134],"ratios":[130],"commonly":[131],"found":[132],"show":[136],"performs":[139],"just":[140],"as":[141,143],"good":[142],"SIC":[144,168],"GICS":[146,170],"terms":[148],"inter-":[150],"intra-industry":[152],"homogeneity,":[153],"especially":[154],"higher":[157],"level":[158],"clustering.":[160],"Given":[161],"that,":[162],"we":[163],"claim":[164],"outperforms":[167],"four":[172],"aspects:":[173],"process":[174],"automation,":[175],"objectivity,":[176],"flexibility,":[178],"result":[180],"interpretability.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}