{"id":"https://openalex.org/W3094948551","doi":"https://doi.org/10.1186/s40537-020-00369-8","title":"CatBoost for big data: an interdisciplinary review","display_name":"CatBoost for big data: an interdisciplinary review","publication_year":2020,"publication_date":"2020-11-04","ids":{"openalex":"https://openalex.org/W3094948551","doi":"https://doi.org/10.1186/s40537-020-00369-8","mag":"3094948551","pmid":"https://pubmed.ncbi.nlm.nih.gov/33169094"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-020-00369-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00369-8","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00369-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00369-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047489766","display_name":"John Hancock","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John T. Hancock","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL USA","Florida Atlantic University, 777 Glades Road, Boca Raton, FL, USA"],"raw_orcid":"https://orcid.org/0000-0003-0699-3042","affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089170562","display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL USA","Florida Atlantic University, 777 Glades Road, Boca Raton, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047489766"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":53.7173,"has_fulltext":true,"cited_by_count":1579,"citation_normalized_percentile":{"value":0.99907984,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"94","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9962999820709229,"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":0.7900855541229248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6581400632858276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6109368205070496},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5715113282203674},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5524348020553589},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4890747666358948},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4108414649963379},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2192196249961853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900855541229248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6581400632858276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6109368205070496},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5715113282203674},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5524348020553589},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4890747666358948},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4108414649963379},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2192196249961853}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s40537-020-00369-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00369-8","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00369-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmid:33169094","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33169094","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of big data","raw_type":null},{"id":"pmh:oai:doaj.org/article:ebdb8a3940d645b7bdc9666d018ada1e","is_oa":true,"landing_page_url":"https://doaj.org/article/ebdb8a3940d645b7bdc9666d018ada1e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 7, Iss 1, Pp 1-45 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7610170","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7610170","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Big Data","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s40537-020-00369-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00369-8","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00369-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310801","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387"},{"id":"https://openalex.org/F4320317380","display_name":"Universidad del Atl\u00e1ntico","ror":"https://ror.org/05mm1w714"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094948551.pdf","grobid_xml":"https://content.openalex.org/works/W3094948551.grobid-xml"},"referenced_works_count":116,"referenced_works":["https://openalex.org/W33489621","https://openalex.org/W1678356000","https://openalex.org/W1728842521","https://openalex.org/W1736726159","https://openalex.org/W1873332500","https://openalex.org/W1973782578","https://openalex.org/W1981276685","https://openalex.org/W1988790447","https://openalex.org/W1990836268","https://openalex.org/W1993127575","https://openalex.org/W1997648776","https://openalex.org/W2019655958","https://openalex.org/W2022604714","https://openalex.org/W2030278443","https://openalex.org/W2070493638","https://openalex.org/W2087240369","https://openalex.org/W2101807845","https://openalex.org/W2108949035","https://openalex.org/W2112796928","https://openalex.org/W2119821739","https://openalex.org/W2123504579","https://openalex.org/W2125055259","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2132166479","https://openalex.org/W2135017136","https://openalex.org/W2136939460","https://openalex.org/W2137959503","https://openalex.org/W2143426320","https://openalex.org/W2148143831","https://openalex.org/W2149591630","https://openalex.org/W2153579005","https://openalex.org/W2153635508","https://openalex.org/W2164641162","https://openalex.org/W2166349035","https://openalex.org/W2176654591","https://openalex.org/W2186436755","https://openalex.org/W2259090596","https://openalex.org/W2263936035","https://openalex.org/W2292531381","https://openalex.org/W2295598076","https://openalex.org/W2296609147","https://openalex.org/W2302185643","https://openalex.org/W2329983047","https://openalex.org/W2339725977","https://openalex.org/W2387462954","https://openalex.org/W2542459869","https://openalex.org/W2557283755","https://openalex.org/W2612690371","https://openalex.org/W2618851150","https://openalex.org/W2740236269","https://openalex.org/W2745244103","https://openalex.org/W2768348081","https://openalex.org/W2782767340","https://openalex.org/W2788544268","https://openalex.org/W2789758093","https://openalex.org/W2798889782","https://openalex.org/W2887302654","https://openalex.org/W2889664499","https://openalex.org/W2892312135","https://openalex.org/W2899434936","https://openalex.org/W2904507906","https://openalex.org/W2909445826","https://openalex.org/W2910992412","https://openalex.org/W2911964244","https://openalex.org/W2914059076","https://openalex.org/W2919984788","https://openalex.org/W2923128516","https://openalex.org/W2932586048","https://openalex.org/W2936503027","https://openalex.org/W2942851257","https://openalex.org/W2944749462","https://openalex.org/W2949435021","https://openalex.org/W2954751351","https://openalex.org/W2962200422","https://openalex.org/W2964022491","https://openalex.org/W2966139567","https://openalex.org/W2967899527","https://openalex.org/W2970803510","https://openalex.org/W2974631082","https://openalex.org/W2974916584","https://openalex.org/W2979966241","https://openalex.org/W2981048847","https://openalex.org/W2984610816","https://openalex.org/W2986990569","https://openalex.org/W2991103266","https://openalex.org/W2998161714","https://openalex.org/W3000295761","https://openalex.org/W3000345023","https://openalex.org/W3004930195","https://openalex.org/W3004933906","https://openalex.org/W3005455537","https://openalex.org/W3007553532","https://openalex.org/W3008987849","https://openalex.org/W3011375118","https://openalex.org/W3011832258","https://openalex.org/W3013997935","https://openalex.org/W3014440691","https://openalex.org/W3016737821","https://openalex.org/W3020873385","https://openalex.org/W3084540277","https://openalex.org/W3087818250","https://openalex.org/W3091855223","https://openalex.org/W3094948551","https://openalex.org/W3098922039","https://openalex.org/W3101033813","https://openalex.org/W3102031602","https://openalex.org/W3102476541","https://openalex.org/W3104181340","https://openalex.org/W3105646565","https://openalex.org/W3132165956","https://openalex.org/W4237831789","https://openalex.org/W4247993926","https://openalex.org/W4248437541","https://openalex.org/W4250750670","https://openalex.org/W4294305479"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084","https://openalex.org/W3003361536"],"abstract_inverted_index":{"Gradient":[0],"Boosted":[1],"Decision":[2,125],"Trees":[3],"(GBDT's)":[4],"are":[5],"a":[6,43,98,124,192,230],"powerful":[7],"tool":[8],"for":[9,65],"classification":[10,151],"and":[11,24,37,88,148,152,169],"regression":[12,153],"tasks":[13,135],"in":[14,31,57,97,150,160,191,208,229],"Big":[15,70,86],"Data.":[16,71],"Researchers":[17],"should":[18],"be":[19],"familiar":[20],"with":[21],"the":[22,46,170,212,219],"strengths":[23],"weaknesses":[25],"of":[26,29,45,48,120,172,206,214],"current":[27],"implementations":[28],"GBDT's":[30],"order":[32],"to":[33,76,85,132,167,180,185,189,201,227],"use":[34],"them":[35],"effectively":[36],"make":[38,178],"successful":[39],"contributions.":[40],"CatBoost":[41,64,81,96,106,129,163,190,207,228],"is":[42,130,164,179,218],"member":[44],"family":[47],"GBDT":[49],"machine":[50,66,133],"learning":[51,67,134],"ensemble":[52],"techniques.":[53],"Since":[54],"its":[55,165],"debut":[56],"late":[58],"2018,":[59],"researchers":[60,197],"have":[61],"successfully":[62],"used":[63],"studies":[68,93,104,187,223],"involving":[69,136],"We":[72],"take":[73,181],"this":[74,217],"opportunity":[75],"review":[77],"recent":[78],"research":[79],"on":[80,162],"as":[82,101,103,123],"it":[83],"relates":[84],"Data,":[87],"learn":[89,115],"best":[90,213],"practices":[91],"from":[92,117],"that":[94,222],"cast":[95],"positive":[99],"light,":[100],"well":[102],"where":[105],"does":[107],"not":[108],"outshine":[109],"other":[110],"techniques,":[111],"since":[112],"we":[113,158,177],"can":[114],"lessons":[116],"both":[118],"types":[119],"scenarios.":[121],"Furthermore,":[122],"Tree":[126],"based":[127],"algorithm,":[128],"well-suited":[131],"categorical,":[137],"heterogeneous":[138],"data.":[139],"Recent":[140],"work":[141],"across":[142],"multiple":[143],"disciplines":[144],"illustrates":[145],"CatBoost's":[146],"effectiveness":[147],"shortcomings":[149],"tasks.":[154],"Another":[155],"important":[156],"issue":[157],"expose":[159],"literature":[161],"sensitivity":[166],"hyper-parameters":[168],"importance":[171],"hyper-parameter":[173],"tuning.":[174],"One":[175],"contribution":[176],"an":[182,198],"interdisciplinary":[183],"approach":[184],"cover":[186],"related":[188,226],"single":[193,231],"work.":[194],"This":[195],"provides":[196],"in-depth":[199],"understanding":[200],"help":[202],"clarify":[203],"proper":[204],"application":[205],"solving":[209],"problems.":[210],"To":[211],"our":[215],"knowledge,":[216],"first":[220],"survey":[221],"all":[224],"works":[225],"publication.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":155},{"year":2025,"cited_by_count":640},{"year":2024,"cited_by_count":389},{"year":2023,"cited_by_count":222},{"year":2022,"cited_by_count":119},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}