{"id":"https://openalex.org/W4362454848","doi":"https://doi.org/10.1587/transinf.2022iip0001","title":"A Methodology on Converting 10-K Filings into a Machine Learning Dataset and Its Applications","display_name":"A Methodology on Converting 10-K Filings into a Machine Learning Dataset and Its Applications","publication_year":2023,"publication_date":"2023-03-31","ids":{"openalex":"https://openalex.org/W4362454848","doi":"https://doi.org/10.1587/transinf.2022iip0001"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2022iip0001","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2022iip0001","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022IIP0001/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022IIP0001/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058662732","display_name":"Mustafa Sami KACAR","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153056","display_name":"KTO Karatay University","ror":"https://ror.org/054341q84","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210153056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mustafa SAMI KACAR","raw_affiliation_strings":["Computer Eng. Dept., KTO Karatay Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Eng. Dept., KTO Karatay Univ","institution_ids":["https://openalex.org/I4210153056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075923116","display_name":"Semih Yumu\u015fak","orcid":"https://orcid.org/0000-0002-8878-4991"},"institutions":[{"id":"https://openalex.org/I4210153056","display_name":"KTO Karatay University","ror":"https://ror.org/054341q84","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210153056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Semih YUMUSAK","raw_affiliation_strings":["Computer Eng. Dept., KTO Karatay Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Eng. Dept., KTO Karatay Univ","institution_ids":["https://openalex.org/I4210153056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008064383","display_name":"Halife Kodaz","orcid":"https://orcid.org/0000-0001-8602-4262"},"institutions":[{"id":"https://openalex.org/I4210117254","display_name":"Konya Technical University","ror":"https://ror.org/02s82rs08","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210117254"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Halife KODAZ","raw_affiliation_strings":["Computer Eng. Dept., Konya Techinical Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Eng. Dept., Konya Techinical Univ","institution_ids":["https://openalex.org/I4210117254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3002,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58451738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"E106.D","issue":"4","first_page":"477","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13794","display_name":"Financial Reporting and XBRL","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13794","display_name":"Financial Reporting and XBRL","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"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/T10081","display_name":"Auditing, Earnings Management, Governance","score":0.9628000259399414,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9484000205993652,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8444852828979492},{"id":"https://openalex.org/keywords/xbrl","display_name":"XBRL","score":0.717007040977478},{"id":"https://openalex.org/keywords/publication","display_name":"Publication","score":0.7032056450843811},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5405908823013306},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4934634268283844},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4701155722141266},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4518558084964752},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.42109423875808716},{"id":"https://openalex.org/keywords/stock-exchange","display_name":"Stock exchange","score":0.4185780882835388},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3857727646827698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37563109397888184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3516245484352112},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33769863843917847},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2220233678817749},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.1965792179107666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8444852828979492},{"id":"https://openalex.org/C2777264242","wikidata":"https://www.wikidata.org/wiki/Q959950","display_name":"XBRL","level":2,"score":0.717007040977478},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.7032056450843811},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5405908823013306},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4934634268283844},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4701155722141266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4518558084964752},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.42109423875808716},{"id":"https://openalex.org/C200870193","wikidata":"https://www.wikidata.org/wiki/Q11691","display_name":"Stock exchange","level":2,"score":0.4185780882835388},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3857727646827698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37563109397888184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3516245484352112},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33769863843917847},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2220233678817749},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.1965792179107666},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1587/transinf.2022iip0001","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2022iip0001","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022IIP0001/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},{"id":"pmh:oai:eprints.soton.ac.uk:477504","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/477504/1/E106.D_2022IIP0001.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:acikerisim.karatay.edu.tr:20.500.12498/8287","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.12498/8287","pdf_url":null,"source":{"id":"https://openalex.org/S7407055354","display_name":"KTO Karatay University Institutional Archive","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1587/transinf.2022IIP0001","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2022iip0001","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2022iip0001","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022IIP0001/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4362454848.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1981728002","https://openalex.org/W2040315127","https://openalex.org/W2162256707","https://openalex.org/W2192483911","https://openalex.org/W2418927623","https://openalex.org/W2585414899","https://openalex.org/W2625464253","https://openalex.org/W2794297791","https://openalex.org/W3004735358","https://openalex.org/W3119490827","https://openalex.org/W3121227176","https://openalex.org/W3122905632","https://openalex.org/W3123028750","https://openalex.org/W3123132665","https://openalex.org/W3124219329","https://openalex.org/W3210002909","https://openalex.org/W4220965125","https://openalex.org/W4248083651","https://openalex.org/W4285137661"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W3092506759","https://openalex.org/W2390914021","https://openalex.org/W2389417819","https://openalex.org/W3195278891"],"abstract_inverted_index":{"Companies":[0],"listed":[1],"on":[2,148],"the":[3,14,22,27,41,63,67,70,77,80,83,109,114,133,138,149,160,163,167,173,178,185],"stock":[4],"exchange":[5],"are":[6,35,135,187],"required":[7],"to":[8,37,61,93,107,158,172],"share":[9],"their":[10],"annual":[11],"reports":[12,65,85,111],"with":[13],"U.S.":[15],"Securities":[16],"and":[17,49,79,103,112,184],"Exchange":[18],"Commission":[19],"(SEC)":[20],"within":[21],"first":[23],"three":[24],"months":[25],"following":[26],"fiscal":[28],"year.":[29],"These":[30],"reports,":[31],"namely":[32],"10-K":[33,52],"Filings,":[34],"presented":[36,136],"public":[38],"interest":[39],"by":[40],"SEC":[42],"through":[43],"an":[44],"Electronic":[45],"Data":[46],"Gathering,":[47],"Analysis,":[48],"Retrieval":[50],"database.":[51],"Filings":[53],"use":[54,113,145],"standard":[55,75],"file":[56,71],"formats":[57,72],"(xbrl,":[58],"html,":[59],"pdf)":[60],"publish":[62],"financial":[64,84,110],"of":[66,82,125,162],"companies.":[68],"Although":[69],"propose":[73],"a":[74,94,100,144],"structure,":[76],"content":[78],"meta-data":[81],"(e.g.":[86],"tag":[87],"names)":[88],"is":[89,182],"not":[90],"strictly":[91],"bound":[92],"pre-defined":[95],"schema.":[96],"This":[97],"study":[98],"proposes":[99],"data":[101,104,116,140],"collection":[102],"preprocessing":[105],"method":[106],"semantify":[108],"collected":[115],"for":[117,189],"further":[118,190],"analysis":[119,124],"(i.e.":[120],"machine":[121,153,175],"learning).":[122],"The":[123],"eight":[126],"different":[127,152],"datasets,":[128,150],"which":[129],"were":[130,156],"created":[131],"during":[132],"study,":[134],"using":[137],"proposed":[139],"transformation":[141],"methods.":[142],"As":[143],"case,":[146],"based":[147],"five":[151],"learning":[154,176],"algorithms":[155],"utilized":[157],"predict":[159],"existence":[161],"corresponding":[164],"company":[165],"in":[166],"S&P":[168],"500":[169],"index.":[170],"According":[171],"strong":[174],"results,":[177],"dataset":[179],"generation":[180],"methodology":[181],"successful":[183],"datasets":[186],"ready":[188],"use.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-04-05T00:00:00"}
