{"id":"https://openalex.org/W2309832917","doi":"https://doi.org/10.1145/2908812.2908918","title":"Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science","display_name":"Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science","publication_year":2016,"publication_date":"2016-07-20","ids":{"openalex":"https://openalex.org/W2309832917","doi":"https://doi.org/10.1145/2908812.2908918","mag":"2309832917"},"language":"en","primary_location":{"id":"doi:10.1145/2908812.2908918","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2908812.2908918","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2908918&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference 2016","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2908918&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028297977","display_name":"Randal S. Olson","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Randal S. Olson","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066288697","display_name":"Nathan Bartley","orcid":"https://orcid.org/0000-0002-6450-5476"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Bartley","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023718023","display_name":"Ryan J. Urbanowicz","orcid":"https://orcid.org/0000-0002-0487-5555"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan J. Urbanowicz","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032971510","display_name":"Jason H. Moore","orcid":"https://orcid.org/0000-0002-5015-1099"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason H. Moore","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028297977"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":33.0671,"has_fulltext":true,"cited_by_count":558,"citation_normalized_percentile":{"value":0.99780046,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"485","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9902999997138977,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9706000089645386,"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":0.7499616146087646},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.7289972901344299},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7189594507217407},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6157588958740234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5934017300605774},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5047537088394165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46790584921836853},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4397214949131012},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4007294476032257},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1427593231201172},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13929378986358643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499616146087646},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7289972901344299},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7189594507217407},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6157588958740234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5934017300605774},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5047537088394165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46790584921836853},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4397214949131012},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4007294476032257},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1427593231201172},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13929378986358643},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2908812.2908918","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2908812.2908918","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2908918&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference 2016","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2908812.2908918","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2908812.2908918","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2908918&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference 2016","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G299099718","display_name":null,"funder_award_id":"LM009012","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3831681186","display_name":null,"funder_award_id":"LM009012, LM010098, and EY022300","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6682602594","display_name":null,"funder_award_id":"LM010098","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8919309667","display_name":null,"funder_award_id":"EY022300","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320316861","display_name":"University of Pennsylvania Health System","ror":"https://ror.org/04h81rw26"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2309832917.pdf","grobid_xml":"https://content.openalex.org/works/W2309832917.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1554944419","https://openalex.org/W1569757501","https://openalex.org/W2051346631","https://openalex.org/W2055936450","https://openalex.org/W2057261601","https://openalex.org/W2084150578","https://openalex.org/W2097998348","https://openalex.org/W2100604298","https://openalex.org/W2101234009","https://openalex.org/W2109042184","https://openalex.org/W2114917617","https://openalex.org/W2117362191","https://openalex.org/W2126071695","https://openalex.org/W2126105956","https://openalex.org/W2126964466","https://openalex.org/W2168696093","https://openalex.org/W2182353144","https://openalex.org/W2182361439","https://openalex.org/W2210969396","https://openalex.org/W2338065342","https://openalex.org/W2559655401","https://openalex.org/W2604272474","https://openalex.org/W2787894218","https://openalex.org/W2950182411","https://openalex.org/W2997591727","https://openalex.org/W3120740533","https://openalex.org/W6634207727","https://openalex.org/W6674385629","https://openalex.org/W6688611412"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2071821326","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397"],"abstract_inverted_index":{"As":[0,131],"the":[1,29,39,105,110],"field":[2],"of":[3,31,38,43,66],"data":[4,71],"science":[5],"continues":[6],"to":[7,22,98,114],"grow,":[8],"there":[9],"will":[10],"be":[11],"an":[12,49,136],"ever-increasing":[13],"demand":[14],"for":[15,35,112],"tools":[16],"that":[17,77,84],"make":[18],"machine":[19,44,81,92,142],"learning":[20,82,93,143],"accessible":[21],"non-experts.":[23],"In":[24,73],"this":[25,133],"paper,":[26],"we":[27,75],"introduce":[28],"concept":[30],"tree-based":[32],"pipeline":[33,144],"optimization":[34],"automating":[36,141],"one":[37],"most":[40],"tedious":[41],"parts":[42],"learning--pipeline":[45],"design.":[46,145],"We":[47,107],"implement":[48],"open":[50],"source":[51],"Tree-based":[52],"Pipeline":[53],"Optimization":[54],"Tool":[55],"(TPOT)":[56],"in":[57],"Python":[58],"and":[59,68],"demonstrate":[60],"its":[61],"effectiveness":[62],"on":[63],"a":[64,86,90],"series":[65],"simulated":[67],"real-world":[69],"benchmark":[70],"sets.":[72],"particular,":[74],"show":[76],"TPOT":[78,113],"can":[79],"design":[80,115],"pipelines":[83,118,126],"provide":[85],"significant":[87],"improvement":[88],"over":[89],"basic":[91],"analysis":[94],"while":[95],"requiring":[96],"little":[97],"no":[99],"input":[100],"nor":[101],"prior":[102],"knowledge":[103],"from":[104],"user.":[106],"also":[108],"address":[109],"tendency":[111],"overly":[116],"complex":[117],"by":[119],"integrating":[120],"Pareto":[121],"optimization,":[122],"which":[123],"produces":[124],"compact":[125],"without":[127],"sacrificing":[128],"classification":[129],"accuracy.":[130],"such,":[132],"work":[134],"represents":[135],"important":[137],"step":[138],"toward":[139],"fully":[140]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":57},{"year":2024,"cited_by_count":78},{"year":2023,"cited_by_count":91},{"year":2022,"cited_by_count":72},{"year":2021,"cited_by_count":91},{"year":2020,"cited_by_count":67},{"year":2019,"cited_by_count":56},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":12}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}