{"id":"https://openalex.org/W4384026552","doi":"https://doi.org/10.1109/msr59073.2023.00022","title":"NICHE: A Curated Dataset of Engineered Machine Learning Projects in Python","display_name":"NICHE: A Curated Dataset of Engineered Machine Learning Projects in Python","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4384026552","doi":"https://doi.org/10.1109/msr59073.2023.00022"},"language":"en","primary_location":{"id":"doi:10.1109/msr59073.2023.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr59073.2023.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5009224648","display_name":"Ratnadira Widyasari","orcid":"https://orcid.org/0000-0001-8190-5458"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ratnadira Widyasari","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008695791","display_name":"Zhou Yang","orcid":"https://orcid.org/0000-0001-5938-1918"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhou Yang","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034736998","display_name":"Ferdian Thung","orcid":"https://orcid.org/0000-0002-5566-3819"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ferdian Thung","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643723","display_name":"Sheng Qin Sim","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sheng Qin Sim","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019603770","display_name":"Fiona Wee","orcid":"https://orcid.org/0000-0001-9161-1955"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fiona Wee","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000131899","display_name":"Camellia Lok","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Camellia Lok","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001478588","display_name":"Jack Phan","orcid":"https://orcid.org/0000-0001-5977-6004"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jack Phan","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013154077","display_name":"Haodi Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haodi Qi","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019251977","display_name":"Constance Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Constance Tan","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062570738","display_name":"Qijin Tay","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qijin Tay","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["Singapore Management University,School of Computing and Information System","School of Computing and Information System, Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information System","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":5.0609,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9646984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9990000128746033,"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":0.9990000128746033,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13650","display_name":"Computational Physics and Python Applications","score":0.961899995803833,"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/python","display_name":"Python (programming language)","score":0.8520957231521606},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.7431108355522156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6443228125572205},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5675979256629944},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5358494520187378},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5305405259132385},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5162277221679688},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45119708776474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4408545196056366},{"id":"https://openalex.org/keywords/niche","display_name":"Niche","score":0.4101408123970032},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.38839805126190186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.345203161239624},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12297949194908142}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8520957231521606},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.7431108355522156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6443228125572205},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5675979256629944},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5358494520187378},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5305405259132385},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5162277221679688},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45119708776474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4408545196056366},{"id":"https://openalex.org/C153991713","wikidata":"https://www.wikidata.org/wiki/Q17142856","display_name":"Niche","level":2,"score":0.4101408123970032},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.38839805126190186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.345203161239624},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12297949194908142},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msr59073.2023.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr59073.2023.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1914969610","https://openalex.org/W2026096417","https://openalex.org/W2047988765","https://openalex.org/W2118174895","https://openalex.org/W2140952846","https://openalex.org/W2143612262","https://openalex.org/W2146511370","https://openalex.org/W2384495648","https://openalex.org/W2559885217","https://openalex.org/W2601908482","https://openalex.org/W2759963882","https://openalex.org/W2890432166","https://openalex.org/W2940740603","https://openalex.org/W2953212509","https://openalex.org/W3035250811","https://openalex.org/W3091074642","https://openalex.org/W3095209159","https://openalex.org/W3103719551","https://openalex.org/W3104284241","https://openalex.org/W3105133011","https://openalex.org/W4221159558","https://openalex.org/W4286530321","https://openalex.org/W4295312788","https://openalex.org/W6766978945","https://openalex.org/W7009029286"],"related_works":["https://openalex.org/W2794103424","https://openalex.org/W4245435724","https://openalex.org/W1996530509","https://openalex.org/W3028317537","https://openalex.org/W2389515972","https://openalex.org/W2055301889","https://openalex.org/W2341492732","https://openalex.org/W2557718140","https://openalex.org/W67092138","https://openalex.org/W4225687299"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"has":[3,8],"gained":[4],"much":[5],"attention":[6],"and":[7,95],"been":[9,32],"incorporated":[10],"into":[11],"our":[12],"daily":[13],"lives.":[14],"While":[15],"there":[16,30],"are":[17,108],"numerous":[18],"publicly":[19],"available":[20],"ML":[21,41,59,76,112,128],"projects":[22,38,42,92],"on":[23,79],"open":[24],"source":[25],"platforms":[26],"such":[27,50],"as":[28,93,97,119],"GitHub,":[29],"have":[31],"limited":[33,47],"attempts":[34],"in":[35,110],"filtering":[36],"those":[37],"to":[39,57,125],"curate":[40],"of":[43,49,74,82,90],"high":[44],"quality.":[45],"The":[46],"availability":[48],"a":[51,69,120],"high-quality":[52,111],"dataset":[53,72,100],"poses":[54],"an":[55],"obstacle":[56],"understanding":[58],"projects.":[60,77,113,129],"To":[61],"help":[62,102],"clear":[63],"this":[64],"obstacle,":[65],"we":[66,87],"present":[67],"NICHE,":[68],"manually":[70],"labelled":[71],"consisting":[73],"572":[75],"Based":[78],"the":[80,105],"evidence":[81],"good":[83],"software":[84],"engineering":[85],"practices,":[86],"label":[88],"441":[89],"these":[91],"engineered":[94,127],"131":[96],"non-engineered.":[98],"This":[99],"can":[101,115],"researchers":[103],"understand":[104],"practices":[106],"that":[107],"adopted":[109],"It":[114],"also":[116],"be":[117],"used":[118],"benchmark":[121],"for":[122],"classifiers":[123],"designed":[124],"identify":[126]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}