{"id":"https://openalex.org/W4388539339","doi":"https://doi.org/10.1145/3630252","title":"Learning from Very Little Data: On the Value of Landscape Analysis for Predicting Software Project Health","display_name":"Learning from Very Little Data: On the Value of Landscape Analysis for Predicting Software Project Health","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4388539339","doi":"https://doi.org/10.1145/3630252"},"language":"en","primary_location":{"id":"doi:10.1145/3630252","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630252","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630252","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630252","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030345696","display_name":"Andre Lustosa","orcid":"https://orcid.org/0000-0003-1202-3130"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andre Lustosa","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0000-0003-1202-3130","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077008083","display_name":"Tim Menzies","orcid":"https://orcid.org/0000-0002-5040-3196"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Menzies","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0000-0002-5040-3196","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":3.0578,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92931878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"33","issue":"3","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/hyperparameter","display_name":"Hyperparameter","score":0.8039610981941223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7351622581481934},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5543053150177002},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4887564182281494},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4681824743747711},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45729386806488037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4221249222755432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3582068085670471},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35163041949272156}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8039610981941223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351622581481934},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5543053150177002},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4887564182281494},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4681824743747711},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45729386806488037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4221249222755432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3582068085670471},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35163041949272156},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630252","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630252","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630252","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3630252","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630252","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630252","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2600861235","display_name":"SHF:Small: Mega-Transfer: On the Value of Learning from 10,000+ Software Projects","funder_award_id":"1908762","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388539339.pdf","grobid_xml":"https://content.openalex.org/works/W4388539339.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W47175876","https://openalex.org/W1437335841","https://openalex.org/W1479807131","https://openalex.org/W1541789800","https://openalex.org/W1595159159","https://openalex.org/W1972475286","https://openalex.org/W1999379336","https://openalex.org/W2016944307","https://openalex.org/W2036229801","https://openalex.org/W2044258615","https://openalex.org/W2072736957","https://openalex.org/W2097670073","https://openalex.org/W2097998348","https://openalex.org/W2106411961","https://openalex.org/W2138428785","https://openalex.org/W2148143831","https://openalex.org/W2150337126","https://openalex.org/W2161032864","https://openalex.org/W2167081989","https://openalex.org/W2344072768","https://openalex.org/W2348136092","https://openalex.org/W2398941234","https://openalex.org/W2484124863","https://openalex.org/W2519440759","https://openalex.org/W2536441188","https://openalex.org/W2551680670","https://openalex.org/W2621485502","https://openalex.org/W2741772737","https://openalex.org/W2751688213","https://openalex.org/W2761479024","https://openalex.org/W2794089287","https://openalex.org/W2799059048","https://openalex.org/W2897289627","https://openalex.org/W2902316941","https://openalex.org/W2914608582","https://openalex.org/W2915649569","https://openalex.org/W2945843801","https://openalex.org/W2949676527","https://openalex.org/W2959468682","https://openalex.org/W2963715041","https://openalex.org/W2964097096","https://openalex.org/W2970928015","https://openalex.org/W2984353870","https://openalex.org/W2997546679","https://openalex.org/W3007313497","https://openalex.org/W3011054152","https://openalex.org/W3019296792","https://openalex.org/W3040394052","https://openalex.org/W3049429073","https://openalex.org/W3101835309","https://openalex.org/W3116361147","https://openalex.org/W3123511746","https://openalex.org/W3161746459","https://openalex.org/W3175215277","https://openalex.org/W3215804261","https://openalex.org/W4205909203","https://openalex.org/W4221145227","https://openalex.org/W4221145890","https://openalex.org/W4225706361","https://openalex.org/W4250503569","https://openalex.org/W4283368911","https://openalex.org/W4291213652","https://openalex.org/W4312769170","https://openalex.org/W6674385629","https://openalex.org/W6676179485","https://openalex.org/W6750676154"],"related_works":["https://openalex.org/W2602382373","https://openalex.org/W3003615511","https://openalex.org/W4285827128","https://openalex.org/W3198113463","https://openalex.org/W2787698406","https://openalex.org/W2963844355","https://openalex.org/W4361251046","https://openalex.org/W3095116576","https://openalex.org/W98577079","https://openalex.org/W4301772239"],"abstract_inverted_index":{"When":[0],"data":[1,33,89,288],"is":[2,111],"scarce,":[3],"software":[4],"analytics":[5,230],"can":[6,63,70,216],"make":[7,64],"many":[8,65],"mistakes.":[9],"For":[10,139],"example,":[11,140],"consider":[12],"learning":[13,236],"predictors":[14],"for":[15,34,141],"open":[16],"source":[17],"project":[18,142,250],"health":[19,143],"(e.g.,":[20,41,123,231],"the":[21,88,92,96,195,200,214,225,245,261],"number":[22,149,154,161],"of":[23,44,53,95,107,150,155,162,182,199,247,263,270],"closed":[24,156,163],"pull":[25,164],"requests":[26],"in":[27,257,276],"12":[28],"months":[29],"time).":[30],"The":[31,56,127],"training":[32,54],"this":[35,264],"task":[36],"may":[37],"be":[38,71],"very":[39,238],"small":[40,239],"5":[42],"years":[43],"data,":[45],"collected":[46],"every":[47],"month":[48],"means":[49],"just":[50],"60":[51],"rows":[52],"data).":[55],"models":[57],"generated":[58],"from":[59,104,237],"such":[60,145],"tiny":[61],"datasets":[62],"prediction":[66,169],"errors.":[67],"Those":[68],"errors":[69,170,181],"tamed":[72],"by":[73,130],"a":[74,101,267],"landscape":[75,94,229],"analysis":[76],"that":[77,108,187,259],"selects":[78],"better":[79],"learner":[80],"control":[81],"parameters.":[82],"Our":[83],"niSNEAK":[84,110,131,166,188,232,248],"tool":[85],"(a)":[86],"clusters":[87],"to":[90,204,249,266],"find":[91],"general":[93],"hyperparameters,":[97,201],"then":[98,202],"(b)":[99],"explores":[100,244],"few":[102],"representatives":[103],"each":[105],"part":[106],"landscape.":[109],"both":[112],"faster":[113],"and":[114,158,287],"more":[115],"effective":[116],"than":[117,136],"prior":[118],"state-of-the-art":[119],"hyperparameter":[120],"optimization":[121],"algorithms":[122],"FLASH,":[124],"HYPEROPT,":[125],"OPTUNA).":[126],"configurations":[128],"found":[129],"have":[132,178],"far":[133,179],"less":[134,220],"error":[135],"other":[137,176,274],"methods.":[138],"indicators":[144],"as":[146],"C":[147],"=":[148,153,160],"commits,":[151],"I":[152],"issues,":[157],"R":[159],"requests,":[165],"\u2019s":[167],"12-month":[168],"are":[171,289],"{I=0%,":[172],"R=33%":[173],"C=47%},":[174],"whereas":[175],"methods":[177,208],"larger":[180],"{I=61%,R=119%":[183],"C=149%}.":[184],"We":[185],"conjecture":[186],"works":[189],"so":[190],"well":[191],"since":[192],"it":[193],"finds":[194],"most":[196],"informative":[197,221],"regions":[198],"jumps":[203],"those":[205],"regions.":[206],"Other":[207],"(that":[209],"do":[210],"not":[211],"reflect":[212],"over":[213],"landscape)":[215],"waste":[217],"time":[218],"exploring":[219],"options.":[222],"Based":[223],"on":[224,291],"preceding,":[226],"we":[227,254],"recommend":[228],")":[233],"especially":[234],"when":[235],"datasets.":[240],"This":[241],"article":[242],"only":[243],"application":[246,262],"health.":[251],"That":[252],"said,":[253],"see":[255],"nothing":[256],"principle":[258],"prevents":[260],"technique":[265],"wider":[268],"range":[269],"problems.":[271],"To":[272],"assist":[273],"researchers":[275],"repeating,":[277],"improving,":[278],"or":[279],"even":[280],"refuting":[281],"our":[282,285],"results,":[283],"all":[284],"scripts":[286],"available":[290],"GitHub":[292],"at":[293],"https://github.com/zxcv123456qwe/niSneak.":[294]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}