{"id":"https://openalex.org/W83593200","doi":null,"title":"On the effect of data set size on bias and variance in classification learning","display_name":"On the effect of data set size on bias and variance in classification learning","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W83593200","mag":"83593200"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.33.1825","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.1825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cm.deakin.edu.au/webb/Papers/akaw99.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5006972170","display_name":"Damien Brain","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Damien Brain","raw_affiliation_strings":["School of Computing|Mathematics Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing|Mathematics Deakin University","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058054791","display_name":"Geoffrey I. Webb","orcid":"https://orcid.org/0000-0001-9963-5169","observed_orcids":["https://orcid.org/0000-0001-9963-5169"]},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Geoffrey I. Webb","raw_affiliation_strings":["School of Computing|Mathematics Deakin University"],"raw_orcid":"https://orcid.org/0000-0001-9963-5169","affiliations":[{"raw_affiliation_string":"School of Computing|Mathematics Deakin University","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":0.3776,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.65704102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.7285000085830688,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.7285000085830688,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1468999981880188,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.034299999475479126,"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/dataset-size","display_name":"dataset size","score":0.8450000286102295},{"id":"https://openalex.org/keywords/bias-variance-decomposition","display_name":"bias-variance decomposition","score":0.8820000290870667},{"id":"https://openalex.org/keywords/classifiers","display_name":"machine learning classifiers","score":0.7839999794960022},{"id":"https://openalex.org/keywords/large-data-sets","display_name":"large data sets","score":0.9039999842643738},{"id":"https://openalex.org/keywords/generalization-error","display_name":"generalization error","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4779933989048004},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.46800318360328674},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4655839502811432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46221962571144104},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.46188682317733765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43176528811454773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3777928352355957},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.35303646326065063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3215319812297821},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09894084930419922},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.33.1825","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.1825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cm.deakin.edu.au/webb/Papers/akaw99.pdf","raw_type":"text"},{"id":"mag:83593200","doi":null,"is_oa":false,"landing_page_url":"https://www.csse.monash.edu/~webb/Files/BrainWebb99.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1491572923","https://openalex.org/W1500698297","https://openalex.org/W1516193414","https://openalex.org/W1530385206","https://openalex.org/W1625504505","https://openalex.org/W1840338487","https://openalex.org/W1975846642","https://openalex.org/W1990991465","https://openalex.org/W2076118331","https://openalex.org/W2084812512","https://openalex.org/W2112076978","https://openalex.org/W2125055259","https://openalex.org/W2912934387"],"related_works":["https://openalex.org/W7099155200","https://openalex.org/W2132849374","https://openalex.org/W2283184234","https://openalex.org/W1970282669","https://openalex.org/W1656335132","https://openalex.org/W4232744553","https://openalex.org/W2340782330","https://openalex.org/W2393877346","https://openalex.org/W1979152118","https://openalex.org/W7096601179"],"abstract_inverted_index":{"With":[0],"the":[1,44,64,110,116,127],"advent":[2],"of":[3,10,66,118,147],"data":[4,45,53,71,84,96,124,133],"mining,":[5],"machine":[6,22,57,80],"learning":[7,23,58,67,81],"has":[8,60],"come":[9],"age":[11],"and":[12,103,138],"is":[13,48,107],"now":[14,35],"a":[15,26,99],"critical":[16],"technology":[17],"in":[18,25,32,43,63,98],"many":[19],"businesses.":[20],"However,":[21,55],"evolved":[24],"different":[27],"research":[28,59],"context":[29,65],"to":[30,77,82,88,92,149],"that":[31],"which":[33],"it":[34],"finds":[36],"itself":[37],"employed.":[38],"A":[39],"particularly":[40],"important":[41],"problem":[42],"mining":[46],"world":[47],"working":[49],"effectively":[50],"with":[51,94],"large":[52,83,95,123],"sets.":[54,72,125],"most":[56,75],"been":[61],"conducted":[62],"from":[68],"very":[69],"small":[70],"To":[73],"date":[74],"approaches":[76],"scaling":[78],"up":[79],"sets":[85,97],"have":[86],"attempted":[87],"modify":[89],"existing":[90],"algorithms":[91,120],"deal":[93],"more":[100],"computationally":[101],"efficient":[102],"effective":[104],"manner.":[105],"But":[106],"this":[108],"necessarily":[109],"best":[111],"method?":[112],"This":[113],"paper":[114,128],"explores":[115],"possibility":[117],"designing":[119],"specifically":[121],"for":[122,142],"Specifically,":[126],"looks":[129],"at":[130],"how":[131],"increasing":[132],"set":[134],"size":[135],"affects":[136],"bias":[137],"variance":[139],"error":[140],"decompositions":[141],"classification":[143],"algorithms.":[144],"Preliminary":[145],"results":[146],"experiments":[148],"determine":[150],"these":[151],"effects":[152],"are":[153],"presen...":[154]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}