{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T16:08:14Z","timestamp":1774195694040,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,6,6]],"date-time":"2010-06-06T00:00:00Z","timestamp":1275782400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,6,6]]},"DOI":"10.1145\/1807167.1807275","type":"proceedings-article","created":{"date-parts":[[2010,6,8]],"date-time":"2010-06-08T12:37:34Z","timestamp":1276000654000},"page":"987-998","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":102,"title":["Ricardo"],"prefix":"10.1145","author":[{"given":"Sudipto","family":"Das","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, USA"}]},{"given":"Yannis","family":"Sismanis","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, USA"}]},{"given":"Kevin S.","family":"Beyer","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, USA"}]},{"given":"Rainer","family":"Gemulla","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, USA"}]},{"given":"Peter J.","family":"Haas","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, USA"}]},{"given":"John","family":"McPherson","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, USA"}]}],"member":"320","published-online":{"date-parts":[[2010,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"2460","article-title":"DB2 UDB's High Function Business Intelligence in e-Business. IBM Redbook Series","volume":"0","author":"Alur N. R.","year":"2002","unstructured":"N. R. Alur , P. J. Haas , D. Momiroska , P. Read , N. H. Summers , V. Totanes , and C. Zuzarte . DB2 UDB's High Function Business Intelligence in e-Business. IBM Redbook Series , ISBN 0-7384 - 2460 - 2469 , 2002 . N. R. Alur, P. J. Haas, D. Momiroska, P. Read, N. H. Summers, V. Totanes, and C. Zuzarte. DB2 UDB's High Function Business Intelligence in e-Business. IBM Redbook Series, ISBN 0-7384-2460-9, 2002.","journal-title":"ISBN"},{"key":"e_1_3_2_1_2_1","unstructured":"Apache Mahout. http:\/\/lucene.apache.org\/mahout\/.  Apache Mahout. http:\/\/lucene.apache.org\/mahout\/."},{"key":"e_1_3_2_1_3_1","volume-title":"Nonlinear Programming: Analysis and Methods","author":"Avriel M.","year":"2003","unstructured":"M. Avriel . Nonlinear Programming: Analysis and Methods . Dover Publishing , 2003 . M. Avriel. Nonlinear Programming: Analysis and Methods. Dover Publishing, 2003."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281206"},{"key":"e_1_3_2_1_5_1","volume-title":"KDD Cup and Workshop","author":"Bennett J.","year":"2007","unstructured":"J. Bennett and S. Lanning . The Netflix prize . In KDD Cup and Workshop , 2007 . J. Bennett and S. Lanning. The Netflix prize. In KDD Cup and Workshop, 2007."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/0916069"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564419"},{"key":"e_1_3_2_1_8_1","first-page":"281","volume-title":"NIPS","author":"Chu C.-T.","year":"2006","unstructured":"C.-T. Chu , S. K. Kim , Y.-A. Lin , Y. Yu , G. R. Bradski , A. Y. Ng , and K. Olukotun . Map-Reduce for machine learning on multicore . In NIPS , pages 281 -- 288 , 2006 . C.-T. Chu, S. K. Kim, Y.-A. Lin, Y. Yu, G. R. Bradski, A. Y. Ng, and K. Olukotun. Map-Reduce for machine learning on multicore. In NIPS, pages 281--288, 2006."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687576"},{"key":"e_1_3_2_1_10_1","volume-title":"Hadoop World NY","author":"Cunningham J.","year":"2009","unstructured":"J. Cunningham . Hadoop@Visa , Hadoop World NY , 2009 . http:\/\/www.slideshare.net\/cloudera\/hw09-large-scale-transaction-analysis. J. Cunningham. Hadoop@Visa, Hadoop World NY, 2009. http:\/\/www.slideshare.net\/cloudera\/hw09-large-scale-transaction-analysis."},{"key":"e_1_3_2_1_11_1","first-page":"137","volume-title":"OSDI","author":"Dean J.","year":"2004","unstructured":"J. Dean and S. Ghemawat . MapReduce: simplified data processing on large clusters . In OSDI , pages 137 -- 150 , 2004 . J. Dean and S. Ghemawat. MapReduce: simplified data processing on large clusters. In OSDI, pages 137--150, 2004."},{"key":"e_1_3_2_1_12_1","unstructured":"S. Guha. RHIPE - R and Hadoop Integrated Processing Environment. http:\/\/ml.stat.purdue.edu\/rhipe\/.  S. Guha. RHIPE - R and Hadoop Integrated Processing Environment. http:\/\/ml.stat.purdue.edu\/rhipe\/."},{"key":"e_1_3_2_1_13_1","volume-title":"The R FAQ","author":"Hornik K.","year":"2009","unstructured":"K. Hornik . The R FAQ , 2009 . http:\/\/CRAN.R-project.org\/doc\/FAQ\/R-FAQ.html. K. Hornik. The R FAQ, 2009. http:\/\/CRAN.R-project.org\/doc\/FAQ\/R-FAQ.html."},{"key":"e_1_3_2_1_14_1","unstructured":"JAQL\n  : Query Language for JavaScript Object Notation (JSON). http:\/\/code.google.com\/p\/jaql 2009.  JAQL: Query Language for JavaScript Object Notation (JSON). http:\/\/code.google.com\/p\/jaql 2009."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376776"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401944"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557072"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"e_1_3_2_1_20_1","first-page":"505","volume-title":"CScADS Scientific Data and Analytics for Petascale Computing Workshop","author":"Samatova N. F.","year":"2009","unstructured":"N. F. Samatova . pR : Introduction to Parallel R for Statistical Computing . In CScADS Scientific Data and Analytics for Petascale Computing Workshop , pages 505 -- 509 , 2009 . N. F. Samatova. pR: Introduction to Parallel R for Statistical Computing. In CScADS Scientific Data and Analytics for Petascale Computing Workshop, pages 505--509, 2009."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v031.i01"},{"key":"e_1_3_2_1_22_1","volume-title":"CIDR","author":"Stonebraker M.","year":"2009","unstructured":"M. Stonebraker , J. Becla , D. J. DeWitt , K.-T. Lim , D. Maier , O. Ratzesberger , and S. B. Zdonik . Requirements for science data bases and SciDB . In CIDR , 2009 . M. Stonebraker, J. Becla, D. J. DeWitt, K.-T. Lim, D. Maier, O. Ratzesberger, and S. B. Zdonik. Requirements for science data bases and SciDB. In CIDR, 2009."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687609"},{"key":"e_1_3_2_1_24_1","unstructured":"L. Tierney A. J. Rossini N. Li and H. Sevcikova. snow: Simple network of workstations. http:\/\/cran.r-project.org\/web\/packages\/snow\/.  L. Tierney A. J. Rossini N. Li and H. Sevcikova. snow: Simple network of workstations. http:\/\/cran.r-project.org\/web\/packages\/snow\/."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639716"},{"key":"e_1_3_2_1_26_1","volume-title":"CIDR","author":"Zhang Y.","year":"2009","unstructured":"Y. Zhang , H. Herodotou , and J. Yang . RIOT: I\/O-efficient numerical computing without SQL . In CIDR , 2009 . Y. Zhang, H. Herodotou, and J. Yang. RIOT: I\/O-efficient numerical computing without SQL. In CIDR, 2009."}],"event":{"name":"SIGMOD\/PODS '10: International Conference on Management of Data","location":"Indianapolis Indiana USA","acronym":"SIGMOD\/PODS '10","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2010 ACM SIGMOD International Conference on Management of data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1807167.1807275","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1807167.1807275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:39:33Z","timestamp":1750246773000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1807167.1807275"}},"subtitle":["integrating R and Hadoop"],"short-title":[],"issued":{"date-parts":[[2010,6,6]]},"references-count":26,"alternative-id":["10.1145\/1807167.1807275","10.1145\/1807167"],"URL":"https:\/\/doi.org\/10.1145\/1807167.1807275","relation":{},"subject":[],"published":{"date-parts":[[2010,6,6]]},"assertion":[{"value":"2010-06-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}