{"id":"https://openalex.org/W4391096379","doi":"https://doi.org/10.1109/bigdata59044.2023.10386531","title":"Refactoring ETL Flows in The Wild","display_name":"Refactoring ETL Flows in The Wild","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391096379","doi":"https://doi.org/10.1109/bigdata59044.2023.10386531"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386531","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","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/A5093760855","display_name":"Dolev Adas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Dolev Adas","raw_affiliation_strings":["IBM Research,Israel","IBM Research, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research,Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093760856","display_name":"Ohad Eytan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ohad Eytan","raw_affiliation_strings":["IBM Research,Israel","IBM Research, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research,Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016766945","display_name":"Guy Khazma","orcid":"https://orcid.org/0009-0008-1364-5162"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Guy Khazma","raw_affiliation_strings":["University of Toronto at Ontario,Department of Computer Science,Canada","Department of Computer Science, University of Toronto at Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto at Ontario,Department of Computer Science,Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto at Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084645226","display_name":"Josep Samp\u00e9","orcid":"https://orcid.org/0000-0002-6869-9765"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Josep Samp\u00e9","raw_affiliation_strings":["IBM Research,Israel","IBM Research, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research,Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075862099","display_name":"Paula Ta-Shma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Paula Ta-Shma","raw_affiliation_strings":["IBM Research,Israel","IBM Research, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research,Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093760855"],"corresponding_institution_ids":["https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3412222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"57","issue":null,"first_page":"1581","last_page":"1590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9993000030517578,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9993000030517578,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.9447678327560425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.79155433177948},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.601738452911377},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5910562872886658},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5809191465377808},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5321254730224609},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.4659273326396942},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41226649284362793},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3853073716163635},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.36596307158470154},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2428450882434845},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.11333698034286499}],"concepts":[{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.9447678327560425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79155433177948},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.601738452911377},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5910562872886658},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5809191465377808},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5321254730224609},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.4659273326396942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41226649284362793},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3853073716163635},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36596307158470154},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2428450882434845},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.11333698034286499},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386531","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W135031542","https://openalex.org/W1985644065","https://openalex.org/W1996651333","https://openalex.org/W2005725110","https://openalex.org/W2015554754","https://openalex.org/W2108150886","https://openalex.org/W2134244431","https://openalex.org/W2157617915","https://openalex.org/W2168209541","https://openalex.org/W2170726034","https://openalex.org/W2227678696","https://openalex.org/W2296703446","https://openalex.org/W2752054654","https://openalex.org/W3009807113","https://openalex.org/W3027461786","https://openalex.org/W4206547615"],"related_works":["https://openalex.org/W4313549863","https://openalex.org/W2072205733","https://openalex.org/W2052246872","https://openalex.org/W2395465245","https://openalex.org/W2101762871","https://openalex.org/W3176957927","https://openalex.org/W4296534969","https://openalex.org/W4312761314","https://openalex.org/W2476494490","https://openalex.org/W3194667890"],"abstract_inverted_index":{"In":[0,63],"modern":[1],"data-driven":[2],"ecosystems,":[3],"Extract,":[4],"Transform,":[5],"Load":[6],"(ETL)":[7],"flows":[8,18,47],"serve":[9],"as":[10],"the":[11,20,42,54,78,83,86,97,113,116,133,149,165,168],"backbone":[12],"of":[13,23,45,57,61,115,135,164],"data":[14,24,35,119],"integration":[15,120],"pipelines.":[16],"These":[17],"facilitate":[19],"seamless":[21],"movement":[22],"across":[25],"disparate":[26],"systems":[27],"and":[28,94,131],"formats,":[29],"streamlining":[30],"processes":[31],"that":[32],"range":[33],"from":[34],"acquisition":[36],"to":[37,52,104,107,143],"preparation":[38],"for":[39,71,88,141],"analysis.":[40],"However,":[41],"pervasive":[43],"use":[44,110,150],"ETL":[46,72,109],"introduces":[48],"a":[49],"pressing":[50],"challenge-how":[51],"bound":[53],"maintenance":[55,79,145],"cost":[56,146],"an":[58,68,161],"ever-expanding":[59],"number":[60],"flows.":[62,157],"this":[64],"paper,":[65],"we":[66,152],"describe":[67],"end-to-end":[69],"prototype":[70,92],"flow":[73],"refactoring,":[74],"aimed":[75],"at":[76],"reducing":[77],"cost,":[80],"which":[81],"keeps":[82],"human":[84],"in":[85,112],"loop":[87],"refactoring":[89],"decisions.":[90],"Our":[91],"adopts":[93],"significantly":[95],"extends":[96],"gSpan":[98],"Frequent":[99],"Subgraph":[100],"Mining":[101],"(FSM)":[102],"algorithm":[103],"apply":[105],"it":[106],"real-world":[108],"cases":[111,151],"context":[114],"IBM":[117],"DataStage\u2122":[118],"tool.":[121],"We":[122,138,158],"report":[123],"on":[124,148],"real":[125],"customer":[126],"workloads,":[127],"share":[128,160],"their":[129],"statistics":[130],"evaluate":[132],"performance":[134],"our":[136],"prototype.":[137],"found":[139],"potential":[140],"up":[142],"32%":[144],"reduction":[147],"analyzed":[153],"after":[154],"removing":[155],"duplicate":[156],"also":[159],"anonymized":[162],"version":[163],"workloads":[166],"with":[167],"research":[169],"community.":[170]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}