{"id":"https://openalex.org/W4387266791","doi":"https://doi.org/10.1016/j.iswa.2023.200285","title":"Automated invoice processing: Machine learning-based information extraction for long tail suppliers","display_name":"Automated invoice processing: Machine learning-based information extraction for long tail suppliers","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4387266791","doi":"https://doi.org/10.1016/j.iswa.2023.200285"},"language":"en","primary_location":{"id":"doi:10.1016/j.iswa.2023.200285","doi":"https://doi.org/10.1016/j.iswa.2023.200285","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.iswa.2023.200285","pdf_url":null,"source":{"id":"https://openalex.org/S4210234522","display_name":"Intelligent Systems with Applications","issn_l":"2667-3053","issn":["2667-3053"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-40"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Systems with Applications","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.iswa.2023.200285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058044546","display_name":"Felix Krieger","orcid":"https://orcid.org/0000-0002-6360-8115","observed_orcids":["https://orcid.org/0000-0002-6360-8115"]},"institutions":[{"id":"https://openalex.org/I113456305","display_name":"Leuphana University of L\u00fcneburg","ror":"https://ror.org/02w2y2t16","country_code":"DE","type":"education","lineage":["https://openalex.org/I113456305"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Felix Krieger","raw_affiliation_strings":["Institute of Information Systems, Leuphana University of L\u00fcneburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6360-8115","affiliations":[{"raw_affiliation_string":"Institute of Information Systems, Leuphana University of L\u00fcneburg, Germany","institution_ids":["https://openalex.org/I113456305"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102939015","display_name":"Paul Drews","orcid":"https://orcid.org/0000-0002-9845-5024","observed_orcids":["https://orcid.org/0000-0002-9845-5024"]},"institutions":[{"id":"https://openalex.org/I113456305","display_name":"Leuphana University of L\u00fcneburg","ror":"https://ror.org/02w2y2t16","country_code":"DE","type":"education","lineage":["https://openalex.org/I113456305"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paul Drews","raw_affiliation_strings":["Institute of Information Systems, Leuphana University of L\u00fcneburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Systems, Leuphana University of L\u00fcneburg, Germany","institution_ids":["https://openalex.org/I113456305"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085924325","display_name":"Burkhardt Funk","orcid":"https://orcid.org/0000-0001-5855-2666","observed_orcids":["https://orcid.org/0000-0001-5855-2666"]},"institutions":[{"id":"https://openalex.org/I113456305","display_name":"Leuphana University of L\u00fcneburg","ror":"https://ror.org/02w2y2t16","country_code":"DE","type":"education","lineage":["https://openalex.org/I113456305"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Burkhardt Funk","raw_affiliation_strings":["Institute of Information Systems, Leuphana University of L\u00fcneburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Systems, Leuphana University of L\u00fcneburg, Germany","institution_ids":["https://openalex.org/I113456305"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058044546"],"corresponding_institution_ids":["https://openalex.org/I113456305"],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":{"value":815,"currency":"EUR","value_usd":878},"fwci":1.7877,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.8627894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"20","issue":null,"first_page":"200285","last_page":"200285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13287","display_name":"Robotic Process Automation Applications","score":0.01979999989271164,"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/T12734","display_name":"Information Systems and Technology Applications","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/electronic-invoicing","display_name":"electronic invoicing","score":0.7599999904632568},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.8560000061988831},{"id":"https://openalex.org/keywords/data-partitioning","display_name":"data partitioning","score":0.4569999873638153},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C2781456945","wikidata":"https://www.wikidata.org/wiki/Q190581","display_name":"Invoice","level":2,"score":0.7306381464004517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6235142946243286},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5995279550552368},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5091161131858826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49313944578170776},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4829117953777313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47143450379371643},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46826010942459106},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.4231295585632324},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34944647550582886},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25774720311164856},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23650798201560974},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.iswa.2023.200285","doi":"https://doi.org/10.1016/j.iswa.2023.200285","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.iswa.2023.200285","pdf_url":null,"source":{"id":"https://openalex.org/S4210234522","display_name":"Intelligent Systems with Applications","issn_l":"2667-3053","issn":["2667-3053"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-40"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Systems with Applications","raw_type":"journal-article"},{"id":"doi:10.2139/ssrn.4386107","doi":"https://doi.org/10.2139/ssrn.4386107","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.4386107","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:pure.leuphana.de:openaire/75e4eebe-29b8-4ec9-90fa-cd0d3a84d8cd","doi":null,"is_oa":true,"landing_page_url":"http://fis.leuphana.de/de/publications/automated-invoice-processing-machine-learningbased-information-extraction-for-long-tail-suppliers(75e4eebe-29b8-4ec9-90fa-cd0d3a84d8cd).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400489","display_name":"Multilingual Matters (Channel View Publications)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Krieger, F, Drews, P & Funk, B 2023, 'Automated Invoice Processing: Machine Learning-Based Information Extraction for Long Tail Suppliers', Intelligent Systems with Applications, vol. 20, 200285. https://doi.org/10.1016/j.iswa.2023.200285","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:476c5c261b59439e9553eb4ecbd3cb15","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/476c5c261b59439e9553eb4ecbd3cb15","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Intelligent Systems with Applications, Vol 20, Iss , Pp 200285- (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.iswa.2023.200285","doi":"https://doi.org/10.1016/j.iswa.2023.200285","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.iswa.2023.200285","pdf_url":null,"source":{"id":"https://openalex.org/S4210234522","display_name":"Intelligent Systems with Applications","issn_l":"2667-3053","issn":["2667-3053"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-40"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Systems with Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5378999710083008}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W639708223","https://openalex.org/W1537287887","https://openalex.org/W1583837637","https://openalex.org/W1631063262","https://openalex.org/W1806891645","https://openalex.org/W2101234009","https://openalex.org/W2126559945","https://openalex.org/W2131241448","https://openalex.org/W2140190241","https://openalex.org/W2142384583","https://openalex.org/W2505790104","https://openalex.org/W2544860310","https://openalex.org/W2599674900","https://openalex.org/W2626778328","https://openalex.org/W2748159032","https://openalex.org/W2791217785","https://openalex.org/W2797928606","https://openalex.org/W2899575547","https://openalex.org/W2911964244","https://openalex.org/W2913389685","https://openalex.org/W2951087161","https://openalex.org/W2962902328","https://openalex.org/W2963341956","https://openalex.org/W2979826702","https://openalex.org/W2997154779","https://openalex.org/W3034864438","https://openalex.org/W3035377849","https://openalex.org/W3093218477","https://openalex.org/W3113177624","https://openalex.org/W3137110532","https://openalex.org/W3141792086","https://openalex.org/W3155464240","https://openalex.org/W3160293046","https://openalex.org/W3180901325","https://openalex.org/W4205185581","https://openalex.org/W4213009331","https://openalex.org/W4214540501","https://openalex.org/W4231109964","https://openalex.org/W4231290138","https://openalex.org/W4234061504","https://openalex.org/W4237887140","https://openalex.org/W4245031736","https://openalex.org/W4251989754","https://openalex.org/W4254214712","https://openalex.org/W4283792702","https://openalex.org/W4391156274","https://openalex.org/W6680704940","https://openalex.org/W6745159025","https://openalex.org/W6772986468","https://openalex.org/W6773829392","https://openalex.org/W6791432593"],"related_works":["https://openalex.org/W7165260303","https://openalex.org/W3141792086","https://openalex.org/W7115037318","https://openalex.org/W6999328550","https://openalex.org/W7104178985","https://openalex.org/W4317039514","https://openalex.org/W2919096156","https://openalex.org/W7111850663","https://openalex.org/W4416156554","https://openalex.org/W4379386778"],"abstract_inverted_index":{"Automation":[0],"of":[1,4,18,50,52,70,82,102,113,120,190,195,200],"the":[2,31,48,59,65,80,100,110,118,124,151,159,166,188,193,198,201],"processing":[3,49],"incoming":[5],"invoices":[6,51,57,71,83],"promises":[7],"to":[8,63,75,133,187],"yield":[9],"vast":[10],"efficiency":[11],"improvements":[12],"in":[13,34,84,150,158,192],"accounting.Until":[14],"a":[15,90,180],"universal":[16],"adoption":[17,32],"fully":[19],"electronic":[20,35],"invoice":[21,43,78],"exchange":[22],"formats":[23],"has":[24],"been":[25],"achieved,machine":[26],"learning":[27,45],"can":[28],"help":[29],"bridge":[30],"gaps":[33],"invoicing":[36],"by":[37,136],"extracting":[38],"structured":[39],"information":[40,121],"from":[41,106,122],"unstructured":[42],"formats.Machine":[44],"especially":[46],"helps":[47],"suppliers":[53,93],"who":[54],"only":[55],"send":[56],"infrequently,as":[58],"models":[60,156],"are":[61,131],"able":[62],"capture":[64],"semantic":[66],"and":[67,72,94,144,153,178,197],"visual":[68],"cues":[69],"generalize":[73],"them":[74],"previously":[76],"unknown":[77],"layouts.Since":[79],"population":[81],"many":[85],"companies":[86],"is":[87,147],"skewed":[88,137],"toward":[89],"few":[91],"frequent":[92],"their":[95],"layouts,":[96],"this":[97,174],"research":[98,181],"examines":[99],"effects":[101],"training":[103],"data":[104,196],"taken":[105],"such":[107],"populations":[108],"on":[109],"predictive":[111,169],"quality":[112],"different":[114,125],"machine-learning":[115],"approaches":[116],"for":[117],"extraction":[119],"invoices.Comparing":[123],"approaches,":[126],"we":[127,176],"find":[128],"that":[129,183],"they":[130],"affected":[132],"varying":[134],"degrees":[135],"layout":[138],"populations:The":[139],"accuracy":[140],"gap":[141],"between":[142],"in-sample":[143],"out-of-sample":[145],"layouts":[146,191],"much":[148],"higher":[149],"Chargrid":[152],"random":[154],"forest":[155],"than":[157],"LayoutLM":[160],"transformer":[161],"model,":[162],"which":[163],"also":[164],"exhibits":[165],"best":[167],"overall":[168],"quality.":[170],"To":[171],"arrive":[172],"at":[173],"finding,":[175],"designed":[177],"implemented":[179],"pipeline":[182],"pays":[184],"special":[185],"attention":[186],"distribution":[189],"splitting":[194],"evaluation":[199],"models.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-03T00:00:00"}