{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:51:40Z","timestamp":1740099100604,"version":"3.37.3"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319966540"},{"type":"electronic","value":"9783319966557"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-96655-7_1","type":"book-chapter","created":{"date-parts":[[2018,7,14]],"date-time":"2018-07-14T01:51:06Z","timestamp":1531533066000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Introduction to Data Profiling"],"prefix":"10.1007","author":[{"given":"Ziawasch","family":"Abedjan","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,7,15]]},"reference":[{"issue":"4","key":"1_CR1","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/s00778-015-0389-y","volume":"24","author":"Z Abedjan","year":"2015","unstructured":"Abedjan, Z., Golab, L., Naumann, F.: Profiling relational data: a survey. VLDB J. 24(4), 557\u2013581 (2015)","journal-title":"VLDB J."},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Naumann, F.: Advancing the discovery of unique column combinations. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 1565\u20131570 (2011)","DOI":"10.1145\/2063576.2063801"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Abedjan, Z., Schulze, P., Naumann, F.: DFD: efficient functional dependency discovery. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 949\u2013958 (2014)","DOI":"10.1145\/2661829.2661884"},{"key":"1_CR4","unstructured":"Agrawal, D., Bernstein, P., Bertino, E., Davidson, S., Dayal, U., Franklin, M., Gehrke, J., Haas, L., Halevy, A., Han, J., Jagadish, H.V., Labrinidis, A., Madden, S., Papakonstantinou, Y., Patel, J.M., Ramakrishnan, R., Ross, K., Shahabi, C., Suciu, D., Vaithyanathan, S., Widom, J.: Challenges and opportunities with Big Data. Technical report, Computing Community Consortium (2012). \nhttp:\/\/cra.org\/ccc\/docs\/init\/bigdatawhitepaper.pdf"},{"key":"1_CR5","unstructured":"Agrawal, R., Srikant, R.: Fast algorithms for mining association rules in large databases. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 487\u2013499 (1994)"},{"issue":"1","key":"1_CR6","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/0306-4379(87)90014-7","volume":"12","author":"MM Astrahan","year":"1987","unstructured":"Astrahan, M.M., Schkolnick, M., Kyu-Young, W.: Approximating the number of unique values of an attribute without sorting. Inf. Syst. 12(1), 11\u201315 (1987)","journal-title":"Inf. Syst."},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Bauckmann, J., Leser, U., Naumann, F., Tietz, V.: Efficiently detecting inclusion dependencies. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 1448\u20131450 (2007)","DOI":"10.1109\/ICDE.2007.369032"},{"issue":"4","key":"1_CR8","first-page":"551","volume":"78","author":"F Benford","year":"1938","unstructured":"Benford, F.: The law of anomalous numbers. Proc. Am. Philos. Soc. 78(4), 551\u2013572 (1938)","journal-title":"Proc. Am. Philos. Soc."},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Berti-Equille, L., Dasu, T., Srivastava, D.: Discovery of complex glitch patterns: a novel approach to quantitative data cleaning. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 733\u2013744 (2011)","DOI":"10.1109\/ICDE.2011.5767864"},{"key":"1_CR10","unstructured":"Bravo, L., Fan, W., Ma, S.: Extending dependencies with conditions. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 243\u2013254 (2007)"},{"issue":"2","key":"1_CR11","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1145\/253262.253327","volume":"26","author":"S Brin","year":"1997","unstructured":"Brin, S., Motwani, R., Silverstein, C.: Beyond market baskets: generalizing association rules to correlations. SIGMOD Rec. 26(2), 265\u2013276 (1997)","journal-title":"SIGMOD Rec."},{"issue":"1","key":"1_CR12","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1109\/TKDE.2015.2472010","volume":"28","author":"L Caruccio","year":"2016","unstructured":"Caruccio, L., Deufemia, V., Polese, G.: Relaxed functional dependencies - a survey of approaches. IEEE Trans. Knowl. Data Eng. (TKDE) 28(1), 147\u2013165 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"issue":"3","key":"1_CR13","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s10115-006-0039-1","volume":"12","author":"V Chandola","year":"2007","unstructured":"Chandola, V., Kumar, V.: Summarization - compressing data into an informative representation. Knowl. Inf. Syst. 12(3), 355\u2013378 (2007)","journal-title":"Knowl. Inf. Syst."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Chu, X., Ilyas, I., Papotti, P., Ye, Y.: RuleMiner: data quality rules discovery. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 1222\u20131225 (2014)","DOI":"10.1109\/ICDE.2014.6816746"},{"issue":"1\u20133","key":"1_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/1900000004","volume":"4","author":"G Cormode","year":"2011","unstructured":"Cormode, G., Garofalakis, M., Haas, P.J., Jermaine, C.: Synopses for massive data: samples, histograms, wavelets, sketches. Found. Trends Databases 4(1\u20133), 1\u2013294 (2011)","journal-title":"Found. Trends Databases"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Dallachiesa, M., Ebaid, A., Eldawy, A., Elmagarmid, A., Ilyas, I.F., Ouzzani, M., Tang, N.: NADEEF: a commodity data cleaning system. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 541\u2013552 (2013)","DOI":"10.1145\/2463676.2465327"},{"key":"1_CR17","unstructured":"Dasu, T., Johnson, T.: Hunting of the snark: finding data glitches using data mining methods. In: Proceedings of the International Conference on Information Quality (IQ), pp. 89\u201398 (1999)"},{"issue":"2","key":"1_CR18","first-page":"43","volume":"29","author":"T Dasu","year":"2006","unstructured":"Dasu, T., Johnson, T., Marathe, A.: Database exploration using database dynamics. IEEE Data Eng. Bull. 29(2), 43\u201359 (2006)","journal-title":"IEEE Data Eng. Bull."},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Dasu, T., Johnson, T., Muthukrishnan, S., Shkapenyuk, V.: Mining database structure; or, how to build a data quality browser. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 240\u2013251 (2002)","DOI":"10.1145\/564691.564719"},{"issue":"11","key":"1_CR20","doi-asserted-by":"publisher","first-page":"1674","DOI":"10.14778\/2350229.2350279","volume":"5","author":"T Dasu","year":"2012","unstructured":"Dasu, T., Loh, J.M.: Statistical distortion: consequences of data cleaning. Proc. VLDB Endowment (PVLDB) 5(11), 1674\u20131683 (2012)","journal-title":"Proc. VLDB Endowment (PVLDB)"},{"issue":"2","key":"1_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1366102.1366103","volume":"33","author":"W Fan","year":"2008","unstructured":"Fan, W., Geerts, F., Jia, X., Kementsietsidis, A.: Conditional functional dependencies for capturing data inconsistencies. ACM Trans. Database Syst. (TODS) 33(2), 1\u201348 (2008)","journal-title":"ACM Trans. Database Syst. (TODS)"},{"issue":"3","key":"1_CR22","first-page":"139","volume":"12","author":"PA Flach","year":"1999","unstructured":"Flach, P.A., Savnik, I.: Database dependency discovery: a machine learning approach. AI Commun. 12(3), 139\u2013160 (1999)","journal-title":"AI Commun."},{"issue":"10","key":"1_CR23","doi-asserted-by":"publisher","first-page":"937","DOI":"10.14778\/2536206.2536220","volume":"6","author":"Minos Garofalakis","year":"2013","unstructured":"Garofalakis, M., Keren, D., Samoladas, V.: Sketch-based geometric monitoring of distributed stream queries. Proc. VLDB Endowment (PVLDB) 6(10) (2013)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"1_CR24","unstructured":"Giannella, C., Wyss, C.: Finding minimal keys in a relation instance (1999). \nhttp:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=?doi=10.1.1.41.7086"},{"issue":"1\u20132","key":"1_CR25","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.14778\/1920841.1921060","volume":"3","author":"L Golab","year":"2010","unstructured":"Golab, L., Karloff, H., Korn, F., Srivastava, D.: Data auditor: exploring data quality and semantics using pattern tableaux. Proc. VLDB Endowment (PVLDB) 3(1\u20132), 1641\u20131644 (2010)","journal-title":"Proc. VLDB Endowment (PVLDB)"},{"key":"1_CR26","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1145\/777943.777945","volume":"28","author":"D Gunopulos","year":"2003","unstructured":"Gunopulos, D., Khardon, R., Mannila, H., Sharma, R.S.: Discovering all most specific sentences. ACM Trans. Database Syst. (TODS) 28, 140\u2013174 (2003)","journal-title":"ACM Trans. Database Syst. (TODS)"},{"key":"1_CR27","unstructured":"Haas, P.J., Naughton, J.F., Seshadri, S., Stokes, L.: Sampling-based estimation of the number of distinct values of an attribute. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 311\u2013322 (1995)"},{"issue":"2","key":"1_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/335191.335372","volume":"29","author":"J Han","year":"2000","unstructured":"Han, J., Pei, J., Yin, Y.: Mining frequent patterns without candidate generation. SIGMOD Rec. 29(2), 1\u201312 (2000)","journal-title":"SIGMOD Rec."},{"issue":"4","key":"1_CR29","doi-asserted-by":"publisher","first-page":"301","DOI":"10.14778\/2732240.2732248","volume":"7","author":"A Heise","year":"2013","unstructured":"Heise, A., Quian\u00e9-Ruiz, J.-A., Abedjan, Z., Jentzsch, A., Naumann, F.: Scalable discovery of unique column combinations. Proc. VLDB Endowment (PVLDB) 7(4), 301\u2013312 (2013)","journal-title":"Proc. VLDB Endowment (PVLDB)"},{"issue":"12","key":"1_CR30","doi-asserted-by":"publisher","first-page":"1700","DOI":"10.14778\/2367502.2367510","volume":"5","author":"JM Hellerstein","year":"2012","unstructured":"Hellerstein, J.M., R\u00e9, C., Schoppmann, F., Wang, D.Z., Fratkin, E., Gorajek, A., Ng, K.S., Welton, C., Feng, X., Li, K., Kumar, A.: The MADlib analytics library or MAD skills, the SQL. Proc. VLDB Endowment (PVLDB) 5(12), 1700\u20131711 (2012)","journal-title":"Proc. VLDB Endowment (PVLDB)"},{"issue":"1","key":"1_CR31","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/360402.360421","volume":"2","author":"J Hipp","year":"2000","unstructured":"Hipp, J., G\u00fcntzer, U., Nakhaeizadeh, G.: Algorithms for association rule mining - a general survey and comparison. SIGKDD Explor. 2(1), 58\u201364 (2000)","journal-title":"SIGKDD Explor."},{"issue":"2","key":"1_CR32","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1093\/comjnl\/42.2.100","volume":"42","author":"Y Huhtala","year":"1999","unstructured":"Huhtala, Y., K\u00e4rkk\u00e4inen, J., Porkka, P., Toivonen, H.: TANE: an efficient algorithm for discovering functional and approximate dependencies. Comput. J. 42(2), 100\u2013111 (1999)","journal-title":"Comput. J."},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Ilyas, I.F., Markl, V., Haas, P.J., Brown, P., Aboulnaga, A.: CORDS: automatic discovery of correlations and soft functional dependencies. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 647\u2013658 (2004)","DOI":"10.1145\/1007568.1007641"},{"key":"1_CR34","unstructured":"Kache, H., Han, W.-S., Markl, V., Raman, V., Ewen, S.: POP\/FED: progressive query optimization for federated queries in DB2. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 1175\u20131178 (2006)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Kandel, S., Parikh, R., Paepcke, A., Hellerstein, J., Heer, J.: Profiler: integrated statistical analysis and visualization for data quality assessment. In: Proceedings of Advanced Visual Interfaces (AVI), pp. 547\u2013554 (2012)","DOI":"10.1145\/2254556.2254659"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Khoussainova, N., Balazinska, M., Suciu, D.: Towards correcting input data errors probabilistically using integrity constraints. In: Proceedings of the ACM International Workshop on Data Engineering for Wireless and Mobile Access (MobiDE), pp. 43\u201350 (2006)","DOI":"10.1145\/1140104.1140114"},{"key":"1_CR37","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/978-3-319-11558-0_13","volume-title":"Logics in Artificial Intelligence","author":"H Koehler","year":"2014","unstructured":"Koehler, H., Leck, U., Link, S., Prade, H.: Logical foundations of possibilistic keys. In: Ferm\u00e9, E., Leite, J. (eds.) JELIA 2014. LNCS (LNAI), vol. 8761, pp. 181\u2013195. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-11558-0_13"},{"key":"1_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/11617808_7","volume-title":"Journal on Data Semantics V","author":"A Koeller","year":"2006","unstructured":"Koeller, A., Rundensteiner, E.A.: Heuristic strategies for the discovery of inclusion dependencies and other patterns. In: Spaccapietra, S., Atzeni, P., Chu, W.W., Catarci, T., Sycara, K.P. (eds.) Journal on Data Semantics V. LNCS, vol. 3870, pp. 185\u2013210. Springer, Heidelberg (2006). \nhttps:\/\/doi.org\/10.1007\/11617808_7"},{"key":"1_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/3-540-46439-5_24","volume-title":"Advances in Database Technology \u2014 EDBT 2000","author":"S Lopes","year":"2000","unstructured":"Lopes, S., Petit, J.-M., Lakhal, L.: Efficient discovery of functional dependencies and armstrong relations. In: Zaniolo, C., Lockemann, P.C., Scholl, M.H., Grust, T. (eds.) EDBT 2000. LNCS, vol. 1777, pp. 350\u2013364. Springer, Heidelberg (2000). \nhttps:\/\/doi.org\/10.1007\/3-540-46439-5_24"},{"issue":"1","key":"1_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0306-4379(01)00027-8","volume":"27","author":"S Lopes","year":"2002","unstructured":"Lopes, S., Petit, J.-M., Toumani, F.: Discovering interesting inclusion dependencies: application to logical database tuning. Inf. Syst. 27(1), 1\u201319 (2002)","journal-title":"Inf. Syst."},{"issue":"3","key":"1_CR41","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1145\/62061.62063","volume":"20","author":"MV Mannino","year":"1988","unstructured":"Mannino, M.V., Chu, P., Sager, T.: Statistical profile estimation in database systems. ACM Comput. Surv. 20(3), 191\u2013221 (1988)","journal-title":"ACM Comput. Surv."},{"key":"1_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1007\/3-540-45876-X_30","volume-title":"Advances in Database Technology \u2014 EDBT 2002","author":"F Marchi De","year":"2002","unstructured":"De Marchi, F., Lopes, S., Petit, J.-M.: Efficient algorithms for mining inclusion dependencies. In: Jensen, C.S., et al. (eds.) EDBT 2002. LNCS, vol. 2287, pp. 464\u2013476. Springer, Heidelberg (2002). \nhttps:\/\/doi.org\/10.1007\/3-540-45876-X_30"},{"key":"1_CR43","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s10844-007-0048-x","volume":"32","author":"F Marchi De","year":"2009","unstructured":"De Marchi, F., Lopes, S., Petit, J.-M.: Unary and n-ary inclusion dependency discovery in relational databases. J. Intell. Inf. Syst. 32, 53\u201373 (2009)","journal-title":"J. Intell. Inf. Syst."},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"De Marchi, F., Petit, J.-M.: Zigzag: a new algorithm for mining large inclusion dependencies in databases. In: Proceedings of the IEEE International Conference on Data Mining (ICDM), pp. 27\u201334 (2003)","DOI":"10.1109\/ICDM.2003.1250899"},{"issue":"6","key":"1_CR45","doi-asserted-by":"publisher","first-page":"453","DOI":"10.14778\/2732279.2732282","volume":"7","author":"K Morton","year":"2014","unstructured":"Morton, K., Balazinska, M., Grossman, D., Mackinlay, J.: Support the data enthusiast: challenges for next-generation data-analysis systems. Proc. VLDB Endowment (PVLDB) 7(6), 453\u2013456 (2014)","journal-title":"Proc. VLDB Endowment (PVLDB)"},{"issue":"4","key":"1_CR46","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/2590989.2590995","volume":"42","author":"F Naumann","year":"2013","unstructured":"Naumann, F.: Data profiling revisited. SIGMOD Rec. 42(4), 40\u201349 (2013)","journal-title":"SIGMOD Rec."},{"key":"1_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/3-540-44503-X_13","volume-title":"Database Theory \u2014 ICDT 2001","author":"N Novelli","year":"2001","unstructured":"Novelli, N., Cicchetti, R.: FUN: an efficient algorithm for mining functional and embedded dependencies. In: Van den Bussche, J., Vianu, V. (eds.) ICDT 2001. LNCS, vol. 1973, pp. 189\u2013203. Springer, Heidelberg (2001). \nhttps:\/\/doi.org\/10.1007\/3-540-44503-X_13"},{"issue":"12","key":"1_CR48","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.14778\/2824032.2824086","volume":"8","author":"T Papenbrock","year":"2015","unstructured":"Papenbrock, T., Bergmann, T., Finke, M., Zwiener, J., Naumann, F.: Data profiling with metanome. Proc. VLDB Endowment (PVLDB) 8(12), 1860\u20131871 (2015)","journal-title":"Proc. VLDB Endowment (PVLDB)"},{"issue":"10","key":"1_CR49","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.14778\/2794367.2794377","volume":"8","author":"Thorsten Papenbrock","year":"2015","unstructured":"Papenbrock, T., Ehrlich, J., Marten, J., Neubert, T., Rudolph, J.-P., Sch\u00f6nberg, M., Zwiener, J., Naumann, F.: Functional dependency discovery: an experimental evaluation of seven algorithms. Proc. VLDB Endowment (PVLDB) 8(10) (2015)","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"7","key":"1_CR50","doi-asserted-by":"publisher","first-page":"774","DOI":"10.14778\/2752939.2752946","volume":"8","author":"Thorsten Papenbrock","year":"2015","unstructured":"Papenbrock, T., Kruse, S., Quian\u00e9-Ruiz, J.-A., Naumann, F.: Divide & conquer-based inclusion dependency discovery. Proc. VLDB Endowment (PVLDB) 8(7) (2015)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Papenbrock, T., Naumann, F.: A hybrid approach to functional dependency discovery. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 821\u2013833 (2016)","DOI":"10.1145\/2882903.2915203"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Poosala, V., Haas, P.J., Ioannidis, Y.E., Shekita, E.J.: Improved histograms for selectivity estimation of range predicates. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 294\u2013305 (1996)","DOI":"10.1145\/233269.233342"},{"issue":"4","key":"1_CR53","first-page":"3","volume":"23","author":"E Rahm","year":"2000","unstructured":"Rahm, E., Do, H.-H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23(4), 3\u201313 (2000)","journal-title":"IEEE Data Eng. Bull."},{"key":"1_CR54","unstructured":"Raman, V., Hellerstein, J.M.: Potters Wheel: an interactive data cleaning system. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 381\u2013390 (2001)"},{"key":"1_CR55","unstructured":"Rostin, A., Albrecht, O., Bauckmann, J., Naumann, F., Leser, U.: A machine learning approach to foreign key discovery. In: Proceedings of the ACM SIGMOD Workshop on the Web and Databases (WebDB) (2009)"},{"key":"1_CR56","unstructured":"Sismanis, Y., Brown, P., Haas, P.J., Reinwald, B.: GORDIAN: efficient and scalable discovery of composite keys. In: Proceedings of the International Conference on Very Large Databases (VLDB), pp. 691\u2013702 (2006)"},{"key":"1_CR57","unstructured":"Stonebraker, M., Bruckner, D., Ilyas, I.F., Beskales, G., Cherniack, M., Zdonik, S., Pagan, A., Xu, S.: Data curation at scale: the Data Tamer system. In: Proceedings of the Conference on Innovative Data Systems Research (CIDR) (2013)"},{"key":"1_CR58","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1109\/69.553155","volume":"8","author":"MS Chen","year":"1996","unstructured":"Chen, M.S., Hun, J., Yu, P.S.: Data mining: an overview from a database perspective. IEEE Trans. Knowl. Data Eng. (TKDE) 8, 866\u2013883 (1996)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"key":"1_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/3-540-44801-2_11","volume-title":"Data Warehousing and Knowledge Discovery","author":"C Wyss","year":"2001","unstructured":"Wyss, C., Giannella, C., Robertson, E.: FastFDs: a heuristic-driven, depth-first algorithm for mining functional dependencies from relation instances extended abstract. In: Kambayashi, Y., Winiwarter, W., Arikawa, M. (eds.) DaWaK 2001. LNCS, vol. 2114, pp. 101\u2013110. Springer, Heidelberg (2001). \nhttps:\/\/doi.org\/10.1007\/3-540-44801-2_11"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Yakout, M., Elmagarmid, A.K., Neville, J., Ouzzani, M.: GDR: a system for guided data repair. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 1223\u20131226 (2010)","DOI":"10.1145\/1807167.1807325"},{"issue":"2","key":"1_CR61","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s10618-007-0083-9","volume":"16","author":"H Yao","year":"2008","unstructured":"Yao, H., Hamilton, H.J.: Mining functional dependencies from data. Data Min. Knowl. Disc. 16(2), 197\u2013219 (2008)","journal-title":"Data Min. Knowl. Disc."},{"issue":"3","key":"1_CR62","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1109\/69.846291","volume":"12","author":"MJ Zaki","year":"2000","unstructured":"Zaki, M.J.: Scalable algorithms for association mining. IEEE Trans. Knowl. Data Eng. (TKDE) 12(3), 372\u2013390 (2000)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"}],"container-title":["Lecture Notes in Business Information Processing","Business Intelligence and Big Data"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-96655-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,7,14]],"date-time":"2018-07-14T01:51:31Z","timestamp":1531533091000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-96655-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319966540","9783319966557"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-96655-7_1","relation":{},"ISSN":["1865-1348","1865-1356"],"issn-type":[{"type":"print","value":"1865-1348"},{"type":"electronic","value":"1865-1356"}],"subject":[],"published":{"date-parts":[[2018]]}}}