{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:17:48Z","timestamp":1780579068207,"version":"3.54.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030275198","type":"print"},{"value":"9783030275204","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-27520-4_13","type":"book-chapter","created":{"date-parts":[[2019,8,18]],"date-time":"2019-08-18T23:02:41Z","timestamp":1566169361000},"page":"179-188","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["Leveraging the Data Lake: Current State and Challenges"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5726-0685","authenticated-orcid":false,"given":"Corinna","family":"Giebler","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6615-4772","authenticated-orcid":false,"given":"Christoph","family":"Gr\u00f6ger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eva","family":"Hoos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger","family":"Schwarz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernhard","family":"Mitschang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,8,3]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Lee, J., Kao, H.-A., Yang, S.: Service innovation and smart analytics for industry 4.0 and big data environment. In: Proceedings of the 6th CIRP Conference on Industrial Product-Service Systems (2014)","DOI":"10.1016\/j.procir.2014.02.001"},{"key":"13_CR2","unstructured":"Russom, P.: Big data analytics. TDWI best Practices report, fourth Quarter (2011)"},{"key":"13_CR3","unstructured":"Margulies, J.C.: Data as Competitive Advantage. Winterberry Group (October) (2015)"},{"issue":"6","key":"13_CR4","first-page":"56","volume":"9","author":"P Tyagi","year":"2016","unstructured":"Tyagi, P., Demirkan, H.: Data lakes: the biggest big data challenges. Analytics 9(6), 56\u201363 (2016)","journal-title":"Analytics"},{"key":"13_CR5","unstructured":"Dixon, J.: Pentaho, Hadoop, and Data Lakes. https:\/\/jamesdixon.wordpress.com\/2010\/10\/14\/pentaho-hadoop-and-data-lakes\/"},{"key":"13_CR6","unstructured":"Dixon, J.: Data Lakes Revisited. https:\/\/jamesdixon.wordpress.com\/2014\/09\/25\/data-lakes-revisited\/"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Madera, C., Laurent, A.: The next information architecture evolution: the data lake wave. In: Proceedings of the 8th International Conference on Management of Digital EcoSystems (MEDES) (2016)","DOI":"10.1145\/3012071.3012077"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Fang, H.: Managing data lakes in big data era: What\u2019s a data lake and why has it became popular in data management ecosystem. In: Proceedings of the 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER) (2015)","DOI":"10.1109\/CYBER.2015.7288049"},{"issue":"5","key":"13_CR9","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/MIS.2014.82","volume":"29","author":"DE O\u2019Leary","year":"2014","unstructured":"O\u2019Leary, D.E.: Embedding AI and crowdsourcing in the big data lake. IEEE Intell. Syst. 29(5), 70\u201373 (2014)","journal-title":"IEEE Intell. Syst."},{"key":"13_CR10","unstructured":"Terrizzano, I., Schwarz, P., Roth, M., Colino, J.E.: Data wrangling: the challenging journey from the wild to the lake. In: Proceedings of the 7th Biennial Conference on Innovative Data Systems Research (CIDR) (2015)"},{"issue":"3","key":"13_CR11","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s13222-017-0272-7","volume":"17","author":"C Mathis","year":"2017","unstructured":"Mathis, C.: Data lakes. Datenbank-Spektrum. 17(3), 289\u2013293 (2017)","journal-title":"Datenbank-Spektrum."},{"key":"13_CR12","unstructured":"Gr\u00f6ger, C., Hoos, E.: Ganzheitliches metadatenmanagement im data lake: anforderungen, IT-werkzeuge und herausforderungen in der Praxis. In: Proceedings der 18. Fachtagung Datenbanksysteme f\u00fcr Business, Technologie und Web (BTW) (2019)"},{"key":"13_CR13","unstructured":"Lock, M.: Maximizing your data lake with a cloud or hybrid approach. Aberdeen Group (2016)"},{"key":"13_CR14","unstructured":"IBM Analytics: The governed data lake approach. IBM (2016)"},{"key":"13_CR15","unstructured":"Madsen, M.: How to Build an enterprise data lake: important considerations before jumping in. Third Nature Inc. (2015)"},{"key":"13_CR16","unstructured":"Gartner Inc.: Gartner Says Beware of the Data Lake Fallacy (2014). https:\/\/www.gartner.com\/newsroom\/id\/2809117"},{"key":"13_CR17","first-page":"6","volume":"4","author":"P Patel","year":"2017","unstructured":"Patel, P., Wood, G., Diaz, A.: Data lake governance best practices. DZone Guide Big Data - Data Sci. Adv. Analytics 4, 6\u20137 (2017)","journal-title":"DZone Guide Big Data - Data Sci. Adv. Analytics"},{"key":"13_CR18","volume-title":"Governing and Managing Big Data for Analytics and Decision Makers","author":"M Chessell","year":"2014","unstructured":"Chessell, M., Scheepers, F., Nguyen, N., van Kessel, R., van der Starre, R.: Governing and Managing Big Data for Analytics and Decision Makers. IBM, New York (2014)"},{"issue":"3","key":"13_CR19","doi-asserted-by":"publisher","first-page":"209","DOI":"10.15514\/ISPRAS-2016-28(3)-13","volume":"28","author":"AR Topchyan","year":"2016","unstructured":"Topchyan, A.R.: Enabling data driven projects for a modern enterprise. Proc. Inst. Syst. Program. RAS (ISP RAS 2016) 28(3), 209\u2013230 (2016)","journal-title":"Proc. Inst. Syst. Program. RAS (ISP RAS 2016)"},{"key":"13_CR20","first-page":"1","volume":"1","author":"B Stein","year":"2014","unstructured":"Stein, B., Morrison, A.: The enterprise data lake: better integration and deeper analytics. Technol. Forecast Rethinking Integr. 1, 1\u20139 (2014)","journal-title":"Technol. Forecast Rethinking Integr."},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Farid, M., Roati, A., Ilyas, I.F., Hoffmann, H.-F., Reuters, T., Chu, X.: CLAMS: bringing quality to data lakes. In: Proceedings of the 2016 International Conference on Management of Data (SIGMOD) (2016)","DOI":"10.1145\/2882903.2899391"},{"key":"13_CR22","volume-title":"The Enterprise Big Data Lake","author":"A Gorelik","year":"2016","unstructured":"Gorelik, A.: The Enterprise Big Data Lake. O\u2019Reilly Media, Inc., Newton (2016)"},{"key":"13_CR23","volume-title":"Architecting Data Lakes - Data Management Architectures for Advanced Business Use Cases","author":"B Sharma","year":"2018","unstructured":"Sharma, B.: Architecting Data Lakes - Data Management Architectures for Advanced Business Use Cases. O\u2019Reilly Media, Inc., Newton (2018)"},{"key":"13_CR24","volume-title":"Big Data Beyond the Hype","author":"P Zikopoulos","year":"2015","unstructured":"Zikopoulos, P., DeRoos, D., Bienko, C., Buglio, R., Andrews, M.: Big Data Beyond the Hype. McGraw-Hill Education, New York (2015)"},{"key":"13_CR25","volume-title":"Data Lake Architecture - Designing the Data Lake and avoiding the Garbage Dump","author":"B Inmon","year":"2016","unstructured":"Inmon, B.: Data Lake Architecture - Designing the Data Lake and avoiding the Garbage Dump. Technics Publications, New Jersey (2016)"},{"key":"13_CR26","volume-title":"Big Data - Principles and Best Practices Of Scalable Real-Time Data Systems","author":"N Marz","year":"2015","unstructured":"Marz, N., Warren, J.: Big Data - Principles and Best Practices Of Scalable Real-Time Data Systems. Manning Publications Co., New York (2015)"},{"issue":"1","key":"13_CR27","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, C.: Building an industry 4.0 analytics platform. Datenbank-Spektrum 18(1), 5\u201314 (2018)","journal-title":"Datenbank-Spektrum"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Giebler, C., Stach, C., Schwarz, H., Mitschang, B.: BRAID - a hybrid processing architecture for big data. In: Proceedings of the 7th International Conference on Data Science, Technology and Applications (DATA) (2018)","DOI":"10.5220\/0006861802940301"},{"key":"13_CR29","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.infsof.2017.06.001","volume":"90","author":"S Nadal","year":"2017","unstructured":"Nadal, S., et al.: A software reference architecture for semantic-aware Big Data systems. Inf. Softw. Technol. 90, 75\u201392 (2017)","journal-title":"Inf. Softw. Technol."},{"issue":"4","key":"13_CR30","first-page":"17","volume":"19","author":"P Stiglich","year":"2014","unstructured":"Stiglich, P.: Data modeling in the age of big data. Bus. Intell. J. 19(4), 17\u201322 (2014)","journal-title":"Bus. Intell. J."},{"key":"13_CR31","unstructured":"Houle, P.: Data Lakes, Data Ponds, and Data Droplets (2017). http:\/\/ontology2.com\/the-book\/data-lakes-ponds-and-droplets.html"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Cernjeka, K., Jaksic, D., Jovanovic, V.: NoSQL document store translation to data vault based EDW. In: 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) (2018)","DOI":"10.23919\/MIPRO.2018.8400217"},{"key":"13_CR33","volume-title":"Comparison of Data Modeling Methods for a Core Data Warehouse","author":"D Schnider","year":"2014","unstructured":"Schnider, D., Martino, A., Eschermann, M.: Comparison of Data Modeling Methods for a Core Data Warehouse. Trivadis, Basel (2014)"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Gr\u00f6ger, C., Schwarz, H., Mitschang, B.: The deep data warehouse: link-based integration and enrichment of warehouse data and unstructured content. In: Proceedings of the 2014 IEEE 18th International Enterprise Distributed Object Computing Conference (EDOC) (2014)","DOI":"10.1109\/EDOC.2014.36"},{"key":"13_CR35","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/978-3-319-46397-1_4","volume-title":"Conceptual Modeling","author":"Victor Herrero","year":"2016","unstructured":"Herrero, V., Abell\u00f3, A., Romero, O.: NOSQL design for analytical workloads: variability matters. In: Proceedings of the 35th International Conference on Conceptual Modeling (ER) (2016)"},{"issue":"9","key":"13_CR36","doi-asserted-by":"publisher","first-page":"67","DOI":"10.7250\/csimq.2016-9.04","volume":"9","author":"C Quix","year":"2016","unstructured":"Quix, C., Hai, R., Vatov, I.: Metadata extraction and management in data lakes with GEMMS. Complex Syst. Inform. Model. Q. 9(9), 67\u201383 (2016)","journal-title":"Complex Syst. Inform. Model. Q."},{"key":"13_CR37","first-page":"5","volume":"39","author":"A Halevy","year":"2016","unstructured":"Halevy, A., et al.: Managing Google\u2019s data lake: an overview of the goods system. IEEE Data Eng. Bullet. 39, 5\u201314 (2016)","journal-title":"IEEE Data Eng. Bullet."},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Hai, R., Geisler, S., Quix, C.: Constance: an intelligent data lake system. In: Proceedings of the 2016 International Conference on Management of Data (SIGMOD) (2016)","DOI":"10.1145\/2882903.2899389"},{"key":"13_CR39","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.is.2018.02.007","volume":"75","author":"E Gallinucci","year":"2018","unstructured":"Gallinucci, E., Golfarelli, M., Rizzi, S.: Schema profiling of document-oriented databases. Inf. Syst. 75, 13\u201325 (2018)","journal-title":"Inf. Syst."},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Walker, C., Alrehamy, H.: Personal data lake with data gravity pull. In: Proceedings of the 2015 IEEE Fifth International Conference on Big Data and Cloud Computing (BDCloud) IEEE (2015)","DOI":"10.1109\/BDCloud.2015.62"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Nogueira, I., Romdhane, M., Darmont, J.: Modeling data lake metadata with a data vault. In: Proceedings of the 22nd International Database Engineering Applications Symposium (IDEAS) (2018)","DOI":"10.1145\/3216122.3216130"}],"container-title":["Lecture Notes in Computer Science","Big Data Analytics and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27520-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:30:33Z","timestamp":1709811033000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-27520-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030275198","9783030275204"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27520-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"3 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DaWaK","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data Analytics and Knowledge Discovery","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Linz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dawak2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/dexa.org\/dawak2019","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mixed (Single-blind and Double-blind)","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfDriver","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"61","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"12","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2-3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}