{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:38:32Z","timestamp":1740159512448,"version":"3.37.3"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T00:00:00Z","timestamp":1580256000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T00:00:00Z","timestamp":1580256000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Datenbank Spektrum"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s13222-020-00332-0","type":"journal-article","created":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T16:02:53Z","timestamp":1580313773000},"page":"57-69","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Data Lakes auf den Grund gegangen"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5726-0685","authenticated-orcid":false,"given":"Corinna","family":"Giebler","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Gr\u00f6ger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eva","family":"Hoos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rebecca","family":"Eichler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Holger","family":"Schwarz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernhard","family":"Mitschang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,29]]},"reference":[{"key":"332_CR1","volume-title":"Data processing requirements of industry 4.0\u2014use cases for big data applications","author":"P G\u00f6lzer","year":"2015","unstructured":"G\u00f6lzer\u00a0P, Cato\u00a0P, Amberg\u00a0M (2015) Data processing requirements of industry 4.0\u2014use cases for big data applications. Proceedings of the 23th European Conference on Information Systems (ECIS 2015)."},{"key":"332_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2014.02.001","volume-title":"Service innovation and smart Analytics for industry 4.0 and big data environment","author":"J Lee","year":"2014","unstructured":"Lee\u00a0J, Kao\u00a0H\u2011A, Yang\u00a0S (2014) Service innovation and smart Analytics for industry 4.0 and big data environment. Proceedings of the 6th CIRP Conference on Industrial Product-Service Systems."},{"issue":"4","key":"332_CR3","doi-asserted-by":"publisher","first-page":"1891","DOI":"10.1109\/TII.2017.2650204","volume":"13","author":"Z Lv","year":"2017","unstructured":"Lv\u00a0Z, Song\u00a0H, Basanta-Val\u00a0P, Steed\u00a0A, Jo\u00a0M (2017) Next-generation big data Analytics: state of the art, challenges, and future research topics. IEEE Trans Industr Inform 13(4):1891\u20131899","journal-title":"IEEE Trans Industr Inform"},{"key":"332_CR4","series-title":"TDWI best pract. report, 4th quart.","volume-title":"Big data analytics","author":"P Russom","year":"2011","unstructured":"Russom\u00a0P (2011) Big data analytics. TDWI best pract. report, 4th quart."},{"issue":"3","key":"332_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3076253","volume":"50","author":"L Cao","year":"2017","unstructured":"Cao\u00a0L (2017) Data Science. ACM Comput Surv 50(3):1\u201342","journal-title":"ACM Comput Surv"},{"issue":"3","key":"332_CR6","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s13222-017-0272-7","volume":"17","author":"C Mathis","year":"2017","unstructured":"Mathis\u00a0C (2017) Data lakes. Datenbank Spektrum 17(3):289\u2013293","journal-title":"Datenbank Spektrum"},{"key":"332_CR7","volume-title":"The governed data lake approach","author":"IBM Analytics","year":"2016","unstructured":"Analytics\u00a0IBM (2016) The governed data lake approach"},{"issue":"6","key":"332_CR8","first-page":"56","volume":"9","author":"P Tyagi","year":"2016","unstructured":"Tyagi\u00a0P, Demirkan\u00a0H (2016) Data lakes: the biggest big data challenges. Analytics 9(6):56\u201363","journal-title":"Analytics"},{"key":"332_CR9","volume-title":"Data lakes: trends and perspectives","author":"F Ravat","year":"2019","unstructured":"Ravat\u00a0F, Zhao\u00a0Y (2019) Data lakes: trends and perspectives. Proceedings of the 30th International Conference on Database and Expert Systems Applications (DEXA 2019)."},{"key":"332_CR10","volume-title":"Designing and operating a\u00a0data reservoir","author":"M Chessell","year":"2015","unstructured":"Chessell\u00a0M, Jones\u00a0NL, Limburn\u00a0J, Radley\u00a0D, Shan\u00a0K (2015) Designing and operating a\u00a0data reservoir"},{"key":"332_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27520-4_13","volume-title":"Leveraging the data lake\u2014current state and challenges","author":"C Giebler","year":"2019","unstructured":"Giebler\u00a0C, Gr\u00f6ger\u00a0C, Hoos\u00a0E, Schwarz\u00a0H, Mitschang\u00a0B (2019) Leveraging the data lake\u2014current state and challenges. Proceedings of the 21st International Conference on Big Data Analytics and Knowledge Discovery (DaWaK 2019)."},{"key":"332_CR12","doi-asserted-by":"publisher","DOI":"10.3139\/9783446438422","volume-title":"Zukunftsorientierte Unternehmensgestaltung","author":"J Gausemeier","year":"2014","unstructured":"Gausemeier\u00a0J, Plass\u00a0C (2014) Zukunftsorientierte Unternehmensgestaltung. Carl Hanser, M\u00fcnchen"},{"issue":"1","key":"332_CR13","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s13222-018-0273-1","volume":"18","author":"C Gr\u00f6ger","year":"2018","unstructured":"Gr\u00f6ger\u00a0C (2018) Building an industry 4.0 analytics platform. Datenbank Spektrum 18(1):5\u201314","journal-title":"Datenbank Spektrum"},{"key":"332_CR14","volume-title":"Data wrangling: the challenging journey from the wild to the lake","author":"I Terrizzano","year":"2015","unstructured":"Terrizzano\u00a0I, Schwarz\u00a0P, Roth\u00a0M, Colino\u00a0JE (2015) Data wrangling: the challenging journey from the wild to the lake. Proceedings of the 7th Biennial Conference on Innovative Data Systems Research (CIDR\u201915)."},{"issue":"4","key":"332_CR15","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1515\/amcs-2017-0046","volume":"27","author":"J Stefanowski","year":"2017","unstructured":"Stefanowski\u00a0J, Krawiec\u00a0K, Wrembel\u00a0R (2017) Exploring complex and big data. Int J Appl Math Comput Sci 27(4):669\u2013679","journal-title":"Int J Appl Math Comput Sci"},{"issue":"5","key":"332_CR16","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/MIS.2014.82","volume":"29","author":"DE O\u2019Leary","year":"2014","unstructured":"O\u2019Leary\u00a0DE (2014) Embedding AI and Crowdsourcing in the big data lake. IEEE Intell Syst 29(5):70\u201373","journal-title":"IEEE Intell Syst"},{"key":"332_CR17","volume-title":"Master data management","author":"D Loshin","year":"2009","unstructured":"Loshin\u00a0D (2009) Master data management. Elsevier, Amsterdam"},{"key":"332_CR18","doi-asserted-by":"publisher","DOI":"10.3139\/9783446451117","volume-title":"Data warehouse blueprints \u2013 business intelligence in der praxis","author":"D Schnider","year":"2016","unstructured":"Schnider\u00a0D, Jordan\u00a0C, Welker\u00a0P, Wehner\u00a0J (2016) Data warehouse blueprints \u2013 business intelligence in der praxis. Carl Hanser, M\u00fcnchen"},{"issue":"5","key":"332_CR19","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1016\/j.ijinfomgt.2016.04.013","volume":"36","author":"D Larson","year":"2016","unstructured":"Larson\u00a0D, Chang\u00a0V (2016) A review and future direction of agile, business intelligence, analytics and data science. Int J Inf Manage 36(5):700\u2013710","journal-title":"Int J Inf Manage"},{"issue":"4","key":"332_CR20","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.2307\/41703503","volume":"36","author":"H Chen","year":"2012","unstructured":"Chen\u00a0H, Chiang\u00a0RHL, Storey\u00a0VC (2012) Business intelligence and Analytics: from big data to big impact. MIS\u00a0Q 36(4):1165\u20131188","journal-title":"MIS Q"},{"key":"332_CR21","volume-title":"Data lakes\u2014purposes, practices, patterns, and platforms","author":"P Russom","year":"2017","unstructured":"Russom\u00a0P (2017) Data lakes\u2014purposes, practices, patterns, and platforms"},{"key":"332_CR22","unstructured":"Dixon J (2010) Pentaho, Hadoop, and data lakes. https:\/\/jamesdixon.wordpress.com\/2010\/10\/14\/pentaho-hadoop-and-data-lakes\/. Zugegriffen: 22.01.2020"},{"key":"332_CR23","unstructured":"Dixon J (2014) Data lakes revisited. https:\/\/jamesdixon.wordpress.com\/2014\/09\/25\/data-lakes-revisited\/. Zugegriffen: 22.01.2020"},{"key":"332_CR24","doi-asserted-by":"publisher","DOI":"10.1145\/3012071.3012077","volume-title":"The next information architecture evolution: the data lake wave","author":"C Madera","year":"2016","unstructured":"Madera\u00a0C, Laurent\u00a0A (2016) The next information architecture evolution: the data lake wave. Proceedings of the 8th International Conference on Management of Digital EcoSystems (MEDES). ACM, New York"},{"key":"332_CR25","volume-title":"Managing data lakes in big data era: what\u2019s a\u00a0data lake and why has it became popular in data management ecosystem","author":"H Fang","year":"2015","unstructured":"Fang\u00a0H (2015) Managing data lakes in big data era: what\u2019s a\u00a0data lake and why has it became popular in data management ecosystem. Proceedings of the 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER 2015)."},{"key":"332_CR26","volume-title":"Ganzheitliches Metadatenmanagement im Data Lake: Anforderungen, IT-Werkzeuge und Herausforderungen in der Praxis","author":"C Gr\u00f6ger","year":"2019","unstructured":"Gr\u00f6ger\u00a0C, Hoos\u00a0E (2019) Ganzheitliches Metadatenmanagement im Data Lake: Anforderungen, IT-Werkzeuge und Herausforderungen in der Praxis. Proceedings der 18. Fachtagung Datenbanksysteme f\u00fcr Business, Technologie und Web (BTW)."},{"key":"332_CR27","volume-title":"Maximizing your data lake with a\u00a0cloud or hybrid approach","author":"M Lock","year":"2016","unstructured":"Lock\u00a0M (2016) Maximizing your data lake with a\u00a0cloud or hybrid approach"},{"key":"332_CR28","volume-title":"How to build an enterprise data lake: important considerations before jumping in","author":"M Madsen","year":"2015","unstructured":"Madsen\u00a0M (2015) How to build an enterprise data lake: important considerations before jumping in"},{"key":"332_CR29","unstructured":"Gartner Inc. (2014) Gartner says beware of the data lake fallacy. https:\/\/www.gartner.com\/en\/newsroom\/press-releases\/2014-07-28-gartner-says-beware-of-the-data-lake-fallacy. Zugegriffen: 22.01.2020"},{"key":"332_CR30","first-page":"6","volume":"4","author":"P Patel","year":"2017","unstructured":"Patel\u00a0P, Wood\u00a0G, Diaz\u00a0A (2017) Data lake governance best practices. Dzone Guid. to big data\u2014data sci. Adv Anal 4:6\u20137","journal-title":"Adv Anal"},{"key":"332_CR31","volume-title":"Governing and managing big data for analytics and decision makers","author":"M Chessell","year":"2014","unstructured":"Chessell\u00a0M, Scheepers\u00a0F, Nguyen\u00a0N, van Kessel\u00a0R, van der Starre\u00a0R (2014) Governing and managing big data for analytics and decision makers"},{"issue":"3","key":"332_CR32","doi-asserted-by":"publisher","first-page":"209","DOI":"10.15514\/ISPRAS-2016-28(3)-13","volume":"28","author":"AR Topchyan","year":"2016","unstructured":"Topchyan\u00a0AR (2016) Enabling data driven projects for a\u00a0modern enterprise. Proc Inst Syst Progr Ras 28(3):209\u2013230","journal-title":"Proc Inst Syst Progr Ras"},{"key":"332_CR33","volume-title":"Technol Forecast Rethink Integr","author":"B Stein","year":"2014","unstructured":"Stein\u00a0B, Morrison\u00a0A (2014) The enterprise data lake: Better integration and deeper analytics. In: Technol Forecast Rethink Integr, Bd. 1"},{"issue":"4","key":"332_CR34","first-page":"17","volume":"19","author":"P Stiglich","year":"2014","unstructured":"Stiglich\u00a0P (2014) Data modeling in the age of big data. Bus Intell\u00a0J 19(4):17\u201322","journal-title":"Bus Intell J"},{"key":"332_CR35","unstructured":"Houle P (2017) Data lakes, data ponds, and data droplets. http:\/\/ontology2.com\/the-book\/data-lakes-ponds-and-droplets.html. Zugegriffen: 22.01.2020"},{"key":"332_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud.2015.62","volume-title":"Personal data lake with data gravity pull","author":"C Walker","year":"2015","unstructured":"Walker\u00a0C, Alrehamy\u00a0H (2015) Personal data lake with data gravity pull. Proceedings of the 2015 IEEE Fifth International Conference on Big Data and Cloud Computing (BDCloud\u201915)."},{"key":"332_CR37","volume-title":"Modeling data lakes with data vault: practical experiences, assessment, and lessons learned","author":"C Giebler","year":"2019","unstructured":"Giebler\u00a0C, Gr\u00f6ger\u00a0C, Hoos\u00a0E, Schwarz\u00a0H, Mitschang\u00a0B (2019) Modeling data lakes with data vault: practical experiences, assessment, and lessons learned. Proceedings of the 38th Conference on Conceptual Modeling (ER 2019)."},{"key":"332_CR38","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO.2018.8400217","volume-title":"NoSQL document store translation to data vault based EDW","author":"K Cernjeka","year":"2018","unstructured":"Cernjeka\u00a0K, Jaksic\u00a0D, Jovanovic\u00a0V (2018) NoSQL document store translation to data vault based EDW. Proceedings of the 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2018)."},{"key":"332_CR39","volume-title":"The deep data warehouse: link-based integration and enrichment of warehouse data and unstructured content","author":"C Gr\u00f6ger","year":"2014","unstructured":"Gr\u00f6ger\u00a0C, Schwarz\u00a0H, Mitschang\u00a0B (2014) The deep data warehouse: link-based integration and enrichment of warehouse data and unstructured content. Proceedings of the 2014 IEEE 18th International Enterprise Distributed Object Computing Conference (EDOC 2014)."},{"key":"332_CR40","volume-title":"Data lake architecture\u2014designing the data lake and avoiding the garbage dump","author":"B Inmon","year":"2016","unstructured":"Inmon\u00a0B (2016) Data lake architecture\u2014designing the data lake and avoiding the garbage dump (Technics Publications)"},{"key":"332_CR41","volume-title":"Architecting data lakes\u2014data management architectures for advanced business use cases","author":"B Sharma","year":"2018","unstructured":"Sharma\u00a0B (2018) Architecting data lakes\u2014data management architectures for advanced business use cases. O\u2019Reilly, Sebastopol"},{"key":"332_CR42","volume-title":"Big data\u2014principles and best practices of scalable real-time data systems","author":"N Marz","year":"2015","unstructured":"Marz\u00a0N, Warren\u00a0J (2015) Big data\u2014principles and best practices of scalable real-time data systems. Manning, Shelter Island"},{"key":"332_CR43","doi-asserted-by":"publisher","DOI":"10.5220\/0006861802940301","volume-title":"BRAID\u2014a hybrid processing architecture for big data","author":"C Giebler","year":"2018","unstructured":"Giebler\u00a0C, Stach\u00a0C, Schwarz\u00a0H, Mitschang\u00a0B (2018) BRAID\u2014a hybrid processing architecture for big data. Proceedings of the 7th International Conference on Data Science, Technology and Applications (DATA 2018). SCITEPRESS, Set\u00fabal"},{"key":"332_CR44","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.infsof.2017.06.001","volume":"90","author":"S Nadal","year":"2017","unstructured":"Nadal\u00a0S, Herrero\u00a0V, Romero\u00a0O, Abell\u00f3\u00a0A, Franch\u00a0X, Vansummeren\u00a0S, Valerio\u00a0D (2017) A software reference architecture for semantic-aware Big Data systems. Inf Softw Technol 90:75\u201392","journal-title":"Inf Softw Technol"},{"key":"332_CR45","volume-title":"Big data beyond the hype","author":"P Zikopoulos","year":"2015","unstructured":"Zikopoulos\u00a0P, DeRoos\u00a0D, Bienko\u00a0C, Buglio\u00a0R, Andrews\u00a0M (2015) Big data beyond the hype. McGraw-Hill, New York"},{"key":"332_CR46","volume-title":"NoSQL distilled\u2014a brief guide to the emerging world of polyglot persistence","author":"PJ Sadalage","year":"2013","unstructured":"Sadalage\u00a0PJ, Fowler\u00a0M (2013) NoSQL distilled\u2014a brief guide to the emerging world of polyglot persistence. Pearson, London"},{"key":"332_CR47","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.ijinfomgt.2019.07.008","volume":"49","author":"R Abraham","year":"2019","unstructured":"Abraham\u00a0R, Schneider\u00a0J, vom Brocke\u00a0J (2019) Data governance: a conceptual framework, structured view, and research agenda. Int J Inf Manage 49:424\u2013438","journal-title":"Int J Inf Manage"},{"issue":"9","key":"332_CR48","first-page":"67","volume":"9","author":"C Quix","year":"2016","unstructured":"Quix\u00a0C, Hai\u00a0R, Vatov\u00a0I (2016) Metadata extraction and management in data lakes with GEMMS. Complex Syst Inf Model\u00a0Q 9(9):67\u201383","journal-title":"Complex Syst Inf Model Q"},{"key":"332_CR49","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.is.2018.02.007","volume":"75","author":"E Gallinucci","year":"2018","unstructured":"Gallinucci\u00a0E, Golfarelli\u00a0M, Rizzi\u00a0S (2018) Schema profiling of document-oriented databases. Inf Syst 75:13\u201325","journal-title":"Inf Syst"},{"key":"332_CR50","doi-asserted-by":"publisher","DOI":"10.1145\/3216122.3216130","volume-title":"Modeling data lake Metadata with a\u00a0data vault","author":"I Nogueira","year":"2018","unstructured":"Nogueira\u00a0I, Romdhane\u00a0M, Darmont\u00a0J (2018) Modeling data lake Metadata with a\u00a0data vault. Proceedings of the 22nd International Database Engineering Applications Symposium (IDEAS 2018)."},{"key":"332_CR51","volume-title":"Metadata systems for data lakes: models and features","author":"PN Sawadogo","year":"2019","unstructured":"Sawadogo\u00a0PN, Scholly \u00c9, Favre\u00a0C, Ferey \u00c9, Loudcher\u00a0S, Darmont\u00a0J (2019) Metadata systems for data lakes: models and features. Proceedings of the 23rd European Conference on Advances in Databases and Information Systems (ADBIS 2019)."},{"key":"332_CR52","doi-asserted-by":"publisher","DOI":"10.5220\/0007706300720083","volume-title":"Metadata management for textual documents in data lakes","author":"P Sawadogo","year":"2019","unstructured":"Sawadogo\u00a0P, Kibata\u00a0T, Darmont\u00a0J (2019) Metadata management for textual documents in data lakes. Proceedings of the 21st International Conference on Enterprise Information Systems (ICEIS 2019). SCITEPRESS, Set\u00fabal"},{"key":"332_CR53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30278-8_5","volume-title":"Metadata management for data lakes","author":"F Ravat","year":"2019","unstructured":"Ravat\u00a0F, Zhao\u00a0Y (2019) Metadata management for data lakes. Proceedings of the 23rd European Conference on Advances in Databases and Information Systems (ADBIS 2019)."}],"container-title":["Datenbank-Spektrum"],"original-title":[],"language":"de","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-020-00332-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13222-020-00332-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-020-00332-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,28]],"date-time":"2021-01-28T00:32:59Z","timestamp":1611793979000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13222-020-00332-0"}},"subtitle":["Herausforderungen und Forschungsl\u00fccken in der Industriepraxis"],"short-title":[],"issued":{"date-parts":[[2020,1,29]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["332"],"URL":"https:\/\/doi.org\/10.1007\/s13222-020-00332-0","relation":{},"ISSN":["1618-2162","1610-1995"],"issn-type":[{"type":"print","value":"1618-2162"},{"type":"electronic","value":"1610-1995"}],"subject":[],"published":{"date-parts":[[2020,1,29]]},"assertion":[{"value":"9 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}