{"id":"https://openalex.org/W4391266969","doi":"https://doi.org/10.1109/ic3i59117.2023.10398128","title":"Data Engineering: An Overview from a Future Perspective","display_name":"Data Engineering: An Overview from a Future Perspective","publication_year":2023,"publication_date":"2023-09-14","ids":{"openalex":"https://openalex.org/W4391266969","doi":"https://doi.org/10.1109/ic3i59117.2023.10398128"},"language":"en","primary_location":{"id":"doi:10.1109/ic3i59117.2023.10398128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3i59117.2023.10398128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Contemporary Computing and Informatics (IC3I)","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/A5100879246","display_name":"Atishay Jain","orcid":"https://orcid.org/0009-0004-6868-3490"},"institutions":[{"id":"https://openalex.org/I74319210","display_name":"Chitkara University","ror":"https://ror.org/057d6z539","country_code":"IN","type":"education","lineage":["https://openalex.org/I74319210"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Atishay Jain","raw_affiliation_strings":["Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","institution_ids":["https://openalex.org/I74319210"]},{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India","institution_ids":["https://openalex.org/I74319210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058388311","display_name":"Sumit Sumit","orcid":"https://orcid.org/0000-0002-1804-5106"},"institutions":[{"id":"https://openalex.org/I74319210","display_name":"Chitkara University","ror":"https://ror.org/057d6z539","country_code":"IN","type":"education","lineage":["https://openalex.org/I74319210"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit","raw_affiliation_strings":["Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","institution_ids":["https://openalex.org/I74319210"]},{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India","institution_ids":["https://openalex.org/I74319210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075373313","display_name":"Chetna Monga","orcid":"https://orcid.org/0000-0002-0189-817X"},"institutions":[{"id":"https://openalex.org/I74319210","display_name":"Chitkara University","ror":"https://ror.org/057d6z539","country_code":"IN","type":"education","lineage":["https://openalex.org/I74319210"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chetna Monga","raw_affiliation_strings":["Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","institution_ids":["https://openalex.org/I74319210"]},{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India","institution_ids":["https://openalex.org/I74319210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049282609","display_name":"Shikha Mittal","orcid":null},"institutions":[{"id":"https://openalex.org/I74319210","display_name":"Chitkara University","ror":"https://ror.org/057d6z539","country_code":"IN","type":"education","lineage":["https://openalex.org/I74319210"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shikha Mittal","raw_affiliation_strings":["Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","institution_ids":["https://openalex.org/I74319210"]},{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University, Rajpura, Punjab, India","institution_ids":["https://openalex.org/I74319210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74319210"],"apc_list":null,"apc_paid":null,"fwci":2.6816,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9265869,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6835962533950806},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6313237547874451},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.6233927607536316},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.6134679317474365},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.544812023639679},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5418236255645752},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5413603186607361},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.518049955368042},{"id":"https://openalex.org/keywords/information-engineering","display_name":"Information engineering","score":0.5058638453483582},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4866200387477875},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4724695384502411},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47122323513031006},{"id":"https://openalex.org/keywords/data-governance","display_name":"Data governance","score":0.46331262588500977},{"id":"https://openalex.org/keywords/data-architecture","display_name":"Data architecture","score":0.45174384117126465},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.4476366639137268},{"id":"https://openalex.org/keywords/master-data","display_name":"Master data","score":0.4427223801612854},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4300438165664673},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.4205326735973358},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.385692298412323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20969432592391968},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2001376748085022},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.18653109669685364},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.16022545099258423},{"id":"https://openalex.org/keywords/software-architecture","display_name":"Software architecture","score":0.12130972743034363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6835962533950806},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6313237547874451},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.6233927607536316},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.6134679317474365},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.544812023639679},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5418236255645752},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5413603186607361},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.518049955368042},{"id":"https://openalex.org/C5283578","wikidata":"https://www.wikidata.org/wiki/Q60596709","display_name":"Information engineering","level":3,"score":0.5058638453483582},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4866200387477875},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4724695384502411},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47122323513031006},{"id":"https://openalex.org/C196879817","wikidata":"https://www.wikidata.org/wiki/Q872685","display_name":"Data governance","level":4,"score":0.46331262588500977},{"id":"https://openalex.org/C94070970","wikidata":"https://www.wikidata.org/wiki/Q638422","display_name":"Data architecture","level":5,"score":0.45174384117126465},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4476366639137268},{"id":"https://openalex.org/C61871575","wikidata":"https://www.wikidata.org/wiki/Q384093","display_name":"Master data","level":2,"score":0.4427223801612854},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4300438165664673},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.4205326735973358},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.385692298412323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20969432592391968},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2001376748085022},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.18653109669685364},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.16022545099258423},{"id":"https://openalex.org/C35869016","wikidata":"https://www.wikidata.org/wiki/Q846636","display_name":"Software architecture","level":3,"score":0.12130972743034363},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C55356503","wikidata":"https://www.wikidata.org/wiki/Q2136675","display_name":"Reference architecture","level":4,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic3i59117.2023.10398128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3i59117.2023.10398128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Contemporary Computing and Informatics (IC3I)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2117672932","https://openalex.org/W2132741574","https://openalex.org/W2148613597","https://openalex.org/W2902740467","https://openalex.org/W2979417040","https://openalex.org/W3007953154","https://openalex.org/W3008947524","https://openalex.org/W3014616325","https://openalex.org/W3016199669","https://openalex.org/W3020963337","https://openalex.org/W3024601883","https://openalex.org/W3026167168","https://openalex.org/W3026400623","https://openalex.org/W3028640536","https://openalex.org/W3028864969","https://openalex.org/W3030055324","https://openalex.org/W3030899497","https://openalex.org/W3031232306","https://openalex.org/W3031577140","https://openalex.org/W3031648392","https://openalex.org/W3032340379","https://openalex.org/W3039969618","https://openalex.org/W3040007593","https://openalex.org/W3047753861","https://openalex.org/W3049122368","https://openalex.org/W3110072028","https://openalex.org/W3118316820","https://openalex.org/W3125675327","https://openalex.org/W3134770171","https://openalex.org/W3165938138","https://openalex.org/W3167963175","https://openalex.org/W3174292513","https://openalex.org/W3195935404","https://openalex.org/W3201675569","https://openalex.org/W4307141309","https://openalex.org/W4310154077","https://openalex.org/W4316087369","https://openalex.org/W4324044577","https://openalex.org/W4360585389"],"related_works":["https://openalex.org/W2478779260","https://openalex.org/W2603547714","https://openalex.org/W2238520454","https://openalex.org/W4386020734","https://openalex.org/W3198250195","https://openalex.org/W4367303911","https://openalex.org/W3136278994","https://openalex.org/W4377704469","https://openalex.org/W1996705223","https://openalex.org/W3147242980"],"abstract_inverted_index":{"Data":[0,56,84,116,158,231,248],"engineering":[1,76,146,159,188,232],"is":[2,20,130,160,189,233],"now":[3],"an":[4,161,234],"essential":[5,46,162],"subject":[6],"for":[7,167,196,206],"handling,":[8],"processing,":[9],"and":[10,36,42,69,82,92,95,105,119,143,153,181,203,209,222,242,250,257,263],"analysing":[11],"big":[12],"data":[13,18,30,39,49,54,65,75,86,114,135,141,145,168,187,197,207,216,229],"as":[14],"the":[15,103,110,131,150,156,165,194,201,245,268],"amount":[16],"of":[17,29,38,48,64,102,113,134,155,193,260],"collected":[19],"increasing":[21],"exponentially.":[22],"This":[23],"paper":[24],"gives":[25],"a":[26,51,99,190,274],"future-focused":[27],"overview":[28],"engineering.":[31,115,136,230],"The":[32],"creation,":[33],"building,":[34],"upkeep,":[35],"optimization":[37],"architecture,":[40],"infrastructure,":[41],"pipelines":[43,57,217],"are":[44,79,97],"all":[45],"components":[47],"engineering,":[50],"field":[52,236],"within":[53],"science.":[55],"that":[58,78,107,218,237,252],"can":[59,253],"effectively":[60],"process":[61],"massive":[62],"volumes":[63],"from":[66],"diverse":[67],"sources":[68],"formats":[70],"must":[71],"be":[72,266],"built":[73],"using":[74],"techniques":[77],"reliable,":[80],"scalable,":[81],"flexible.":[83],"warehousing,":[85],"modelling,":[87],"SQL":[88],"databases,":[89,91],"NoSQL":[90],"Apache":[93],"Hadoop":[94],"Spark":[96],"just":[98],"few":[100],"examples":[101],"tools":[104,202],"technologies":[106,262],"fall":[108],"under":[109],"broad":[111],"umbrella":[112],"scientists,":[117],"analysts,":[118],"business":[120,220],"users":[121],"should":[122],"have":[123],"rapid":[124],"access":[125],"to":[126,139,174,240,255,271],"correct":[127],"data,":[128],"which":[129,199],"main":[132],"objective":[133],"In":[137,185],"addition":[138],"optimizing":[140],"storage":[142],"performance,":[144],"also":[147],"entails":[148],"guaranteeing":[149],"quality,":[151],"integrity,":[152],"security":[154],"data.":[157],"phase":[163],"in":[164,228,244,267,273],"workflow":[166],"scientists":[169],"since":[170],"it":[171],"enables":[172],"them":[173],"carry":[175],"out":[176],"advanced":[177],"analytics,":[178],"machine":[179],"learning,":[180],"other":[182],"data-driven":[183,275],"operations.":[184],"conclusion,":[186],"vital":[191],"part":[192],"ecosystem":[195],"science,":[198],"offers":[200],"infrastructure":[204],"required":[205],"processing":[208],"analysis.":[210],"Companies":[211],"may":[212],"build":[213],"strong,":[214],"scalable":[215],"foster":[219],"insights":[221],"innovation":[223],"by":[224],"utilizing":[225],"best":[226,269],"practices":[227],"important":[235],"will":[238,265],"continue":[239],"grow":[241],"transform":[243],"coming":[246],"years.":[247],"engineers":[249],"organizations":[251],"adapt":[254],"change":[256],"take":[258],"advantage":[259],"emerging":[261],"trends":[264],"position":[270],"succeed":[272],"future.":[276]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
