{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:31:25Z","timestamp":1783139485653,"version":"3.54.6"},"reference-count":98,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2016,10,13]],"date-time":"2016-10-13T00:00:00Z","timestamp":1476316800000},"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":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1007\/s41060-016-0027-9","type":"journal-article","created":{"date-parts":[[2016,10,13]],"date-time":"2016-10-13T07:18:36Z","timestamp":1476343116000},"page":"145-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":356,"title":["Big data analytics on Apache Spark"],"prefix":"10.1007","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6750-003X","authenticated-orcid":false,"given":"Salman","family":"Salloum","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruslan","family":"Dautov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick Xiaogang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua Zhexue","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,10,13]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","unstructured":"Agarwal, S., Mozafari, B., Panda, A., Milner, H., Madden, S., Stoica, I.: Blinkdb: queries with bounded errors and bounded response times on very large data. In: Proceedings of the 8th ACM European Conference on Computer Systems. ACM, New York, pp 29\u201342 (2013). doi: 10.1145\/2465351.2465355","DOI":"10.1145\/2465351.2465355"},{"key":"27_CR2","unstructured":"Amde, M., Bradley, J.: Scalable decision trees in mllib. https:\/\/databricks.com\/blog\/2014\/09\/29\/scalable-decision-trees-in-mllib.html (2014)"},{"key":"27_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1677-z","author":"I Anagnostopoulos","year":"2016","unstructured":"Anagnostopoulos, I., Zeadally, S., Exposito, E.: Handling big data: research challenges and future directions. J. Supercomput. (2016). doi: 10.1007\/s11227-016-1677-z","journal-title":"J. Supercomput."},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Andrew, G., Gao, J.: Scalable training of l1-regularized log-linear models. In: International Conference on Machine Learning (2007)","DOI":"10.1145\/1273496.1273501"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Apiletti, D., Garza, P., Pulvirenti, F.: New Trends in databases and information systems: ADBIS 2015 Short Papers and Workshops, BigDap, DCSA, GID, MEBIS, OAIS, SW4CH, WISARD, Poitiers, France, September 8\u201311, 2015. Proceedings, Springer International Publishing, Cham, chap A Review of Scalable Approaches for Frequent Itemset Mining, pp. 243\u2013247 (2015)","DOI":"10.1007\/978-3-319-23201-0_27"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Aridhi, S., Nguifo, E.M.: Big graph mining: frameworks and techniques. arXiv preprint arXiv:1602.03072 (2016)","DOI":"10.1016\/j.bdr.2016.07.002"},{"key":"27_CR7","doi-asserted-by":"publisher","unstructured":"Armbrust, M., Ghodsi, A., Zaharia, M., Xin, R.S., Lian, C., Huai, Y., Liu, D., Bradley, J.K., Meng, X., Kaftan, T., Franklin, M.J.: Spark SQL. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data\u2014SIGMOD \u201915, ACM Press, New York, NY, USA, pp. 1383\u20131394. doi: 10.1145\/2723372.2742797 . http:\/\/dl.acm.org\/citation.cfm?id=2723372.2742797 (2015)","DOI":"10.1145\/2723372.2742797"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Armbrust, M., Huai, Y., Liang, C., Xin, R., Zaharia, M.: Deep dive into spark sqls catalyst optimizer. https:\/\/databricks.com\/blog\/2015\/04\/13\/deep-dive-into-spark-sqls-catalyst-optimizer.html (2015)","DOI":"10.1145\/2723372.2742797"},{"key":"27_CR9","unstructured":"Armbrust, M., Fan, W., Xin, R., Zaharia, M.: Introducing spark datasets. https:\/\/databricks.com\/blog\/2016\/01\/04\/introducing-spark-datasets.html (2016)"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Awan, A.J., Brorsson, M., Vlassov, V., Ayguad\u00e9, E.: How data volume affects spark based data analytics on a scale-up server. CoRR arxiv:1507.08340 (2015)","DOI":"10.1007\/978-3-319-29006-5_7"},{"key":"27_CR11","unstructured":"Awan, A.J., Brorsson, M., Vlassov, V., Ayguad\u00e9, E.: Architectural impact on performance of in-memory data analytics: Apache spark case study. CoRR arXiv:1604.08484 (2016)"},{"issue":"7","key":"27_CR12","doi-asserted-by":"publisher","first-page":"553","DOI":"10.14778\/2732286.2732292","volume":"7","author":"M Boehm","year":"2014","unstructured":"Boehm, M., Tatikonda, S., Reinwald, B., Sen, P., Tian, Y., Burdick, D.R., Vaithyanathan, S.: Hybrid parallelization strategies for large-scale machine learning in systemML. Proc. VLDB Endow. 7(7), 553\u2013564 (2014). doi: 10.14778\/2732286.2732292","journal-title":"Proc. VLDB Endow."},{"issue":"1\u20132","key":"27_CR13","doi-asserted-by":"publisher","first-page":"285","DOI":"10.14778\/1920841.1920881","volume":"3","author":"Y Bu","year":"2010","unstructured":"Bu, Y., Howe, B., Balazinska, M., Ernst, M.D.: Haloop: efficient iterative data processing on large clusters. Proc. VLDB Endow. 3(1\u20132), 285\u2013296 (2010). doi: 10.14778\/1920841.1920881","journal-title":"Proc. VLDB Endow."},{"key":"27_CR14","unstructured":"Burdorf, C.: Use of spark mllib for predicting the offlining of digital media. Presentation. https:\/\/spark-summit.org\/2015\/events\/use-of-spark-mllib-for-predicting-the-offlining-of-digital-media\/ (2015)"},{"key":"27_CR15","unstructured":"Busa, N.: Real-time anomaly detection with spark ml and akka. Presentation. https:\/\/spark-summit.org\/eu-2015\/events\/real-time-anomaly-detection-with-spark-ml-and-akka\/ (2015)"},{"key":"27_CR16","doi-asserted-by":"publisher","unstructured":"Capot\u0103, M, Hegeman, T., Iosup, A., Prat-P\u00e9rez, A., Erling, O., Boncz, P.: Graphalytics: a big data benchmark for graph-processing platforms. In: Proceedings of the GRADES\u201915, ACM, New York, NY, USA, GRADES\u201915, pp. 7:1\u20137:6. doi: 10.1145\/2764947.2764954 (2015)","DOI":"10.1145\/2764947.2764954"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Zhan, Y., Faloutsos, C.: R-mat: a recursive model for graph mining. In: In Fourth SIAM International Conference on Data Mining (2004)","DOI":"10.1137\/1.9781611972740.43"},{"key":"27_CR18","unstructured":"Chan, W.: Databricks democratizes data and reduces infrastructure costs for eyeview. https:\/\/databricks.com\/blog\/2016\/02\/03\/databricks-democratizes-data-and-reduces-infrastructure-costs-for-eyeview.html (2016)"},{"key":"27_CR19","doi-asserted-by":"publisher","unstructured":"Cheng, R., Chen, E., Hong, J., Kyrola, A., Miao, Y., Weng, X., Wu, M., Yang, F., Zhou, L., Zhao, F.: Kineograph. In: Proceedings of the 7th ACM european conference on Computer Systems\u2014EuroSys \u201912, ACM Press, New York, NY, USA, p\u00a085. doi: 10.1145\/2168836.2168846 . http:\/\/dl.acm.org\/citation.cfm?id=2168836.2168846 (2012)","DOI":"10.1145\/2168836.2168846"},{"key":"27_CR20","unstructured":"Crankshaw, D., Bailis, P., Gonzalez, J.E., Li, H., Zhang, Z., Franklin, M.J., Ghodsi, A., Jordan, M.I.: The missing piece in complex analytics: low latency, scalable model management and serving with velox. CoRR arxiv:1409.3809 (2014)"},{"key":"27_CR21","unstructured":"Damji, J.: A tale of three apache spark apis: Rdds, dataframes, and datasets. https:\/\/databricks.com\/blog\/2016\/07\/14\/a-tale-of-three-apache-spark-apis-rdds-dataframes-and-datasets.html (2016)"},{"key":"27_CR22","unstructured":"Das, T., Zaharia, M., Wendell, P.: Diving into spark streaming\u2019s execution model. https:\/\/databricks.com\/blog\/2015\/07\/30\/diving-into-spark-streamings-execution-model.html (2015)"},{"key":"27_CR23","unstructured":"Databricks: Databricks spark reference applications. http:\/\/tinyurl.com\/gwzkqxr (2015)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Dave, A.: Graphframes: graph queries in spark sql. Presentation. https:\/\/spark-summit.org\/east-2016\/events\/graphframes-graph-queries-in-spark-sql\/ (2016)","DOI":"10.1145\/2960414.2960416"},{"key":"27_CR25","doi-asserted-by":"publisher","unstructured":"Dave, A., Jindal, A., Li, L.E., Xin, R., Gonzalez, J., Zaharia, M.: Graphframes: an integrated api for mixing graph and relational queries. In: Proceedings of the Fourth International Workshop on Graph Data Management Experiences and Systems, ACM, New York, NY, USA, GRADES \u201916, pp. 2:1\u20132:8. doi: 10.1145\/2960414.2960416 (2016)","DOI":"10.1145\/2960414.2960416"},{"key":"27_CR26","doi-asserted-by":"publisher","unstructured":"Ekanayake, J., Li, H., Zhang, B., Gunarathne, T., Bae, S.H., Qiu, J., Fox, G.: Twister: A runtime for iterative mapreduce. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, ACM, New York, NY, USA, HPDC \u201910, pp. 810\u2013818. doi: 10.1145\/1851476.1851593 (2010)","DOI":"10.1145\/1851476.1851593"},{"issue":"5","key":"27_CR27","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1002\/widm.1134","volume":"4","author":"A Fernndez","year":"2014","unstructured":"Fernndez, A., del Ro, S., Lpez, V., Bawakid, A., del Jesus, M.J., Bentez, J.M., Herrera, F.: Big data with cloud computing: an insight on the computing environment, mapreduce, and programming frameworks. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 4(5), 380\u2013409 (2014). doi: 10.1002\/widm.1134","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Freeman, J.: A platform for large-scale neuroscience. Presentation. https:\/\/spark-summit.org\/2014\/talk\/A-platform-for-large-scale-neuroscience (2014)","DOI":"10.2307\/j.ctt9qh0x7.13"},{"key":"27_CR29","unstructured":"Freeman, J.: Introducing streaming k-means in spark 1.2. https:\/\/databricks.com\/blog\/2015\/01\/28\/introducing-streaming-k-means-in-spark-1-2.html (2015)"},{"key":"27_CR30","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.conb.2015.04.002","volume":"32","author":"J Freeman","year":"2015","unstructured":"Freeman, J.: Open source tools for large-scale neuroscience. Curr. Opin. Neurobiol. 32, 156\u2013163 (2015). doi: 10.1016\/j.conb.2015.04.002 . large-Scale Recording Technology (32)","journal-title":"Curr. Opin. Neurobiol."},{"key":"27_CR31","doi-asserted-by":"crossref","DOI":"10.1002\/9781119254805","volume-title":"Spark: Big Data Cluster Computing in Production","author":"l Ganelin","year":"2016","unstructured":"Ganelin, l: Spark: Big Data Cluster Computing in Production. Wiley, New York (2016)"},{"key":"27_CR32","doi-asserted-by":"publisher","unstructured":"Ghoting, A., Krishnamurthy, R., Pednault, E.P.D., Reinwald, B., Sindhwani, V., Tatikonda, S., Tian, Y., Vaithyanathan, S.: Systemml: Declarative machine learning on mapreduce. In: Abiteboul, S., B\u00f6hm, K., Koch, C., Tan, K. (eds.) Proceedings of the 27th International Conference on Data Engineering, ICDE 2011, April 11\u201316, 2011, Hannover, Germany, IEEE Computer Society, pp. 231\u2013242. doi: 10.1109\/ICDE.2011.5767930 (2011)","DOI":"10.1109\/ICDE.2011.5767930"},{"key":"27_CR33","doi-asserted-by":"publisher","unstructured":"Gonzalez, J.E.: From graphs to tables the design of scalable systems for graph analytics. In: 23rd International World Wide Web Conference, WWW \u201914, Seoul, Republic of Korea, April 7\u201311, 2014, Companion Volume, pp. 1149\u20131150. doi: 10.1145\/2567948.2580059 (2014)","DOI":"10.1145\/2567948.2580059"},{"key":"27_CR34","unstructured":"Gonzalez, J.E., Low, Y., Gu, H., Bickson, D., Guestrin, C.: PowerGraph: distributed graph-parallel computation on natural graphs, pp. 17\u201330. http:\/\/dl.acm.org\/citation.cfm?id=2387880.2387883 (2012)"},{"key":"27_CR35","unstructured":"Gonzalez, J.E., Xin, R.S., Dave, A., Crankshaw, D., Franklin, M.J., Stoica, I.: Graphx: Graph processing in a distributed dataflow framework. In: Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, OSDI\u201914, pp. 599\u2013613. http:\/\/dl.acm.org\/citation.cfm?id=2685048.2685096 (2014)"},{"issue":"1","key":"27_CR36","first-page":"8","volume":"113","author":"S Gopalani","year":"2015","unstructured":"Gopalani, S., Arora, R.: Article: Comparing apache spark and map reduce with performance analysis using k-means. Int. J. Comput. Appl. 113(1), 8\u201311 (2015). (full text available)","journal-title":"Int. J. Comput. Appl."},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Guller, M.: Big Data Analytics with Spark: A Practitioner\u2019s Guide to Using Spark for Large Scale Data Analysis. Apress. https:\/\/books.google.de\/books?id=bNP8rQEACAAJ (2015)","DOI":"10.1007\/978-1-4842-0964-6"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Gulzar, M.A., Interlandi, M., Yoo, S., Tetali, S.D., Condie, T., Millstein, T., Kim, M.: Bigdebug: debugging primitives for interactive big data processing in spark. In: Proceedings of 38th IEEE\/ACM International Conference on Software Engineering, ICSE\u2019 16 (2016)","DOI":"10.1145\/2884781.2884813"},{"key":"27_CR39","unstructured":"Hindman, B., Konwinski, A., Zaharia, M., Ghodsi, A., Joseph, A.D., Katz, R., Shenker, S., Stoica, I.: Mesos: a platform for fine-grained resource sharing in the data center. In: Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201911, pp. 295\u2013308. http:\/\/dl.acm.org\/citation.cfm?id=1972457.1972488 (2011)"},{"key":"27_CR40","unstructured":"Huang, M.: Dynamic community detection for large-scale e-commerce data with spark streaming and graphx. Presentation. https:\/\/spark-summit.org\/2015\/events\/hybrid-community-detection-for-web-scale-e-commerce-using-spark-streaming-and-graphx\/ (2015)"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Interlandi, M., Shah, K., Tetali, S.D., Gulzar, M., Yoo, S., Kim, M., Millstein, T.D., Condie, T.: Titian: Data provenance support in spark. PVLDB 9(3), 216\u2013227. http:\/\/www.vldb.org\/pvldb\/vol9\/p216-interlandi.pdf (2015)","DOI":"10.14778\/2850583.2850595"},{"key":"27_CR42","unstructured":"Ivanov, T., Beer, M.: Evaluating Hive and spark SQL with bigbench. CoRR arXiv:1512.08417 (2015)"},{"key":"27_CR43","doi-asserted-by":"publisher","unstructured":"Iyer, A.P., Li, L.E., Das, T., Stoica, I.: Time-evolving graph processing at scale. In: Proceedings of the Fourth International Workshop on Graph Data Management Experiences and Systems, ACM, New York, NY, USA, GRADES \u201916, pp. 5:1\u20135:6. doi: 10.1145\/2960414.2960419 (2016)","DOI":"10.1145\/2960414.2960419"},{"key":"27_CR44","doi-asserted-by":"publisher","unstructured":"Jarrah, M., Al-Quraan, M., Jararweh, Y., Al-Ayyoub, M.: Medgraph: a graph-based representation and computation to handle large sets of images. Multimedia Tools and Applications, pp. 1\u201317. doi: 10.1007\/s11042-016-3262-0 (2016)","DOI":"10.1007\/s11042-016-3262-0"},{"key":"27_CR45","volume-title":"Learning Spark: Lightning-Fast Big Data Analytics","author":"H Karau","year":"2015","unstructured":"Karau, H., Konwinski, A., Wendell, P., Zaharia, M.: Learning Spark: Lightning-Fast Big Data Analytics, 1st edn. O\u2019Reilly Media, Inc, Sebastopol (2015)","edition":"1"},{"key":"27_CR46","unstructured":"Kim, H., Park, J., Jang, J., Yoon, S.: Deepspark: Spark-based deep learning supporting asynchronous updates and caffe compatibility. CoRR arXiv:1602.08191 (2016)"},{"key":"27_CR47","doi-asserted-by":"publisher","unstructured":"Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Li, Y., Liu, B., Sarawagi, S. (eds.) Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, Nevada, USA, August 24\u201327, 2008, ACM, pp. 426\u2013434. doi: 10.1145\/1401890.1401944 (2008)","DOI":"10.1145\/1401890.1401944"},{"key":"27_CR48","unstructured":"Kraska, T., Talwalkar, A., Duchi, J.C., Griffith, R., Franklin, M.J., Jordan, M.I.: Mlbase: A distributed machine-learning system. In: CIDR. www.cidrdb.org . http:\/\/dblp.uni-trier.de\/db\/conf\/cidr\/cidr2013.html (2013)"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Krishnan, D.R., Quoc, D.L., Bhatotia, P., Fetzer, C., Rodrigues, R.: Incapprox: A data analytics system for incremental approximate computing. In: Proceedings of the 25th International Conference on World Wide Web, International World Wide Web Conferences Steering Committee, pp. 1133\u20131144 (2016)","DOI":"10.1145\/2872427.2883026"},{"key":"27_CR50","unstructured":"Kursar, B.: Data driven\u2014toyota customer 360 insights on apache spark and mllib. Presentation. https:\/\/spark-summit.org\/2015\/events\/keynote-7\/ (2015)"},{"issue":"1","key":"27_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-015-0032-1","volume":"2","author":"S Landset","year":"2015","unstructured":"Landset, S., Khoshgoftaar, T.M., Richter, A.N., Hasanin, T.: A survey of open source tools for machine learning with big data in the hadoop ecosystem. J. Big Data 2(1), 1\u201336 (2015). doi: 10.1186\/s40537-015-0032-1","journal-title":"J. Big Data"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Li, H., Ghodsi, A., Zaharia, M., Shenker, S., Stoica, I.: Tachyon: Reliable, memory speed storage for cluster computing frameworks. In: Proceedings of the ACM Symposium on Cloud Computing, ACM, pp. 1\u201315 (2014)","DOI":"10.1145\/2670979.2670985"},{"key":"27_CR53","doi-asserted-by":"publisher","unstructured":"Li, M., Tan, J., Wang, Y., Zhang, L., Salapura, V.: SparkBench. In: Proceedings of the 12th ACM International Conference on Computing Frontiers\u2014CF \u201915, ACM Press, New York, New York, USA, pp. 1\u20138. doi: 10.1145\/2742854.2747283 (2015)","DOI":"10.1145\/2742854.2747283"},{"key":"27_CR54","doi-asserted-by":"publisher","unstructured":"Li, P., Luo, Y., Zhang, N., Cao, Y.: Heterospark: A heterogeneous cpu\/gpu spark platform for machine learning algorithms. In: 2015 IEEE International Conference on Networking, Architecture and Storage (NAS), pp. 347\u2013348. doi: 10.1109\/NAS.2015.7255222 (2015)","DOI":"10.1109\/NAS.2015.7255222"},{"key":"27_CR55","unstructured":"Low, Y., Gonzalez, J., Kyrola, A., Bickson, D., Guestrin, C., Hellerstein, J.M.: GraphLab: A New Framework for Parallel Machine Learning, pp. 8\u201311. arxiv:1006.4990 (2010)"},{"issue":"8","key":"27_CR56","doi-asserted-by":"publisher","first-page":"716","DOI":"10.14778\/2212351.2212354","volume":"5","author":"Y Low","year":"2012","unstructured":"Low, Y., Bickson, D., Gonzalez, J., Guestrin, C., Kyrola, A., Hellerstein, J.M.: Distributed graphlab: a framework for machine learning and data mining in the cloud. Proc. VLDB Endow. 5(8), 716\u2013727 (2012). doi: 10.14778\/2212351.2212354","journal-title":"Proc. VLDB Endow."},{"key":"27_CR57","doi-asserted-by":"crossref","unstructured":"Malewicz, G., Austern, M.H., Bik, A.J., Dehnert, J.C., Horn, I., Leiser, N., Czajkowski, G.: Pregel. In: Proceedings of the 2010 International Conference on Management of data\u2014SIGMOD \u201910, ACM Press, New York, NY, USA, p 135. http:\/\/dl.acm.org\/citation.cfm?id=1807167.1807184 (2010)","DOI":"10.1145\/1807167.1807184"},{"key":"27_CR58","doi-asserted-by":"publisher","unstructured":"Malewicz, G., Austern, M.H., Bik, A.J., Dehnert, J.C., Horn, I., Leiser, N., Czajkowski, G.: Pregel: A system for large-scale graph processing. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, ACM, New York, NY, USA, SIGMOD \u201910, pp. 135\u2013146. doi: 10.1145\/1807167.1807184 (2010)","DOI":"10.1145\/1807167.1807184"},{"key":"27_CR59","doi-asserted-by":"crossref","unstructured":"Marcu, O.C., Costan, A., Antoniu, G., P\u00e9rez, M.S.: Spark versus Flink: Understanding Performance in Big Data Analytics Frameworks. In: Cluster 2016\u2014The IEEE 2016 International Conference on Cluster Computing, Taipei, Taiwan. https:\/\/hal.inria.fr\/hal-01347638 (2016)","DOI":"10.1109\/CLUSTER.2016.22"},{"key":"27_CR60","unstructured":"Massie, M., Nothaft, F., Hartl, C., Kozanitis, C., Schumacher, A., Joseph, A.D., Patterson, D.A.: Adam: Genomics formats and processing patterns for butt scale computing. Tech. Rep. UCB\/EECS-2013-207, EECS Department, University of California, Berkeley (2013)"},{"key":"27_CR61","unstructured":"Meng, X., Bradley, J., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., Freeman, J., Tsai, D., Amde, M., Owen, S., Xin, D., Xin, R., Franklin, M.J., Zadeh, R., Zaharia, M., Talwalkar, A.: Mllib: Machine learning in apache spark arXiv:1505.06807 (2015)"},{"key":"27_CR62","unstructured":"Moffitt, V.Z., Stoyanovich, J.: Portal: a query language for evolving graphs. arXiv preprint arXiv:1602.00773 (2016)"},{"key":"27_CR63","doi-asserted-by":"crossref","unstructured":"Moffitt, V.Z., Stoyanovich, J.: Towards a distributed infrastructure for evolving graph analytics. https:\/\/www.cs.drexel.edu\/~julia\/documents\/tempweb16.pdf (2016)","DOI":"10.1145\/2872518.2889290"},{"key":"27_CR64","unstructured":"Moritz, P., Nishihara, R., Stoica, I., Jordan, M.I.: Sparknet: Training deep networks in spark. CoRR arXiv:1511.06051 (2015)"},{"issue":"1","key":"27_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12864-015-2269-7","volume":"16","author":"AR O\u2019Brien","year":"2015","unstructured":"O\u2019Brien, A.R., Saunders, N.F.W., Guo, Y., Buske, F.A., Scott, R.J., Bauer, D.C.: Variantspark: population scale clustering of genotype information. BMC Genom. 16(1), 1\u20139 (2015). doi: 10.1186\/s12864-015-2269-7","journal-title":"BMC Genom."},{"key":"27_CR66","unstructured":"Ousterhout, K., Rasti, R., Ratnasamy, S., Shenker, S., Chun, B.G.: Making sense of performance in data analytics frameworks. In: Proceedings of the 12th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201915, pp. 293\u2013307. http:\/\/dl.acm.org\/citation.cfm?id=2789770.2789791 (2015)"},{"key":"27_CR67","doi-asserted-by":"publisher","unstructured":"Palamuttam, R., Mogrovejo, R.M., Mattmann, C., Wilson, B., Whitehall, K., Verma, R., McGibbney, L.J., Ramirez, P.M.: Scispark: applying in-memory distributed computing to weather event detection and tracking. In: 2015 IEEE International Conference on Big Data, Big Data 2015, Santa Clara, CA, USA, October 29-November 1, 2015, IEEE, pp. 2020\u20132026. doi: 10.1109\/BigData.2015.7363983 (2015)","DOI":"10.1109\/BigData.2015.7363983"},{"issue":"1","key":"27_CR68","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1002\/widm.1173","volume":"6","author":"S Ramrez-Gallego","year":"2016","unstructured":"Ramrez-Gallego, S., Garca, S., Mourio-Taln, H., Martnez-Rego, D., Boln-Canedo, V., Alonso-Betanzos, A., Bentez, J.M., Herrera, F.: Data discretization: taxonomy and big data challenge. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 6(1), 5\u201321 (2016). doi: 10.1002\/widm.1173","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"27_CR69","doi-asserted-by":"publisher","unstructured":"Richter, A.N., Khoshgoftaar, T.M., Landset, S., Hasanin, T.: A multi-dimensional comparison of toolkits for machine learning with big data. In: 2015 IEEE International Conference on Information Reuse and Integration, IRI 2015, San Francisco, CA, USA, August 13\u201315, 2015, IEEE, pp. 1\u20138. doi: 10.1109\/IRI.2015.12 (2015)","DOI":"10.1109\/IRI.2015.12"},{"key":"27_CR70","unstructured":"Ryza, S., Laserson, U., Owen, S., Wills, J.: Advanced Analytics with Spark: Patterns for Learning from Data at Scale. O\u2019Reilly Media. https:\/\/books.google.de\/books?id=M0_GBwAAQBAJ (2015)"},{"key":"27_CR71","unstructured":"Salperwyck, C., Maby, S., Cubill\u00e9, J., Lagacherie, M.: Courbospark: Decision tree for time-series on spark. In: Proceedings of the 1st International Workshop on Advanced Analytics and Learning on Temporal Data, AALTD 2015, co-located with The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2015), Porto, Portugal, September 11, 2015. http:\/\/ceur-ws.org\/Vol-1425\/paper15.pdf (2015)"},{"issue":"13","key":"27_CR72","doi-asserted-by":"publisher","first-page":"2110","DOI":"10.14778\/2831360.2831365","volume":"8","author":"J Shi","year":"2015","unstructured":"Shi, J., Qiu, Y., Minhas, U.F., Jiao, L., Wang, C., Reinwald, B., \u00d6zcan, F.: Clash of the titans: Mapreduce vs. spark for large scale data analytics. Proc. VLDB Endow. 8(13), 2110\u20132121 (2015). doi: 10.14778\/2831360.2831365","journal-title":"Proc. VLDB Endow."},{"key":"27_CR73","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.protcy.2015.10.085","volume":"21","author":"R Shyam","year":"2015","unstructured":"Shyam, R., Kumar, S., Poornachandran, P., Soman, K.P.: Apache spark a big data analytics platform for smart grid. Proc. Technol. 21, 171\u2013178 (2015). doi: 10.1016\/j.protcy.2015.10.085","journal-title":"Proc. Technol."},{"key":"27_CR74","unstructured":"Sparks, E.R., Talwalkar, A., Franklin, M.J., Jordan, M.I., Kraska, T.: Tupaq: An efficient planner for large-scale predictive analytic queries. CoRR arXiv:1502.00068 (2015)"},{"key":"27_CR75","doi-asserted-by":"publisher","unstructured":"Sparks, E.R., Talwalkar, A., Haas, D., Franklin, M.J., Jordan, M.I., Kraska, T.: Automating model search for large scale machine learning. In: Proceedings of the Sixth ACM Symposium on Cloud Computing, ACM, New York, NY, USA, SoCC \u201915, pp. 368\u2013380. doi: 10.1145\/2806777.2806945 (2015)","DOI":"10.1145\/2806777.2806945"},{"key":"27_CR76","doi-asserted-by":"publisher","unstructured":"Vavilapalli, V.K., Murthy, A.C., Douglas, C., Agarwal, S., Konar, M., Evans, R., Graves, T., Lowe, J., Shah, H., Seth, S., Saha, B., Curino, C., O\u2019Malley, O., Radia, S., Reed, B., Baldeschwieler, E.: Apache hadoop yarn: yet another resource negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing, ACM, New York, NY, USA, SOCC \u201913, pp. 5:1\u20135:16. doi: 10.1145\/2523616.2523633 (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"27_CR77","doi-asserted-by":"publisher","unstructured":"Venkataraman, S., Yang, Z., Liu, D., Liang, E., Falaki, H., Meng, X., Xin, R., Ghodsi, A., Franklin, M., Stoica, I., Zaharia, M.: Sparkr: Scaling r programs with spark. In: Proceedings of the 2016 International Conference on Management of Data, ACM, New York, NY, USA, SIGMOD \u201916, pp. 1099\u20131104. doi: 10.1145\/2882903.2903740 (2016)","DOI":"10.1145\/2882903.2903740"},{"key":"27_CR78","doi-asserted-by":"publisher","unstructured":"Wang, K., Khan, M.M.H.: Performance prediction for apache spark platform. In: 2015 IEEE 17th International Conference on High Performance Computing and Communications (HPCC), 2015 IEEE 7th International Symposium on Cyberspace Safety and Security (CSS), 2015 IEEE 12th International Conferen on Embedded Software and Systems (ICESS), pp. 166\u2013173. doi: 10.1109\/HPCC-CSS-ICESS.2015.246 (2015)","DOI":"10.1109\/HPCC-CSS-ICESS.2015.246"},{"key":"27_CR79","unstructured":"Xiao, B.: Huawei embraces open-source apache spark. https:\/\/databricks.com\/blog\/2015\/06\/09\/huawei-embraces-open-source-apache-spark.html (2015)"},{"key":"27_CR80","unstructured":"Xin, R.: Spark officially sets a new record in large-scale sorting. https:\/\/databricks.com\/blog\/2014\/11\/05\/spark-officially-sets-a-new-record-in-large-scale-sorting.html (2014)"},{"key":"27_CR81","unstructured":"Xin, R.: Technical preview of apache spark 2.0 now on databricks. https:\/\/databricks.com\/blog\/2016\/05\/11\/apache-spark-2-0-technical-preview-easier-faster-and-smarter.html (2016)"},{"key":"27_CR82","unstructured":"Xin, R., Rosen, J.: Project tungsten: Bringing spark closer to bare metal. Presentation. https:\/\/databricks.com\/blog\/2015\/04\/28\/project-tungsten-bringing-spark-closer-to-bare-metal.html (2015)"},{"key":"27_CR83","doi-asserted-by":"crossref","unstructured":"Xin, R.S., Gonzalez, J.E., Franklin, M.J., Stoica, I.: Graphx: a resilient distributed graph system on spark. In: First International Workshop on Graph Data Management Experiences and Systems, GRADES 2013, co-loated with SIGMOD\/PODS 2013, New York, NY, USA, June 24, 2013, p\u00a02. http:\/\/event.cwi.nl\/grades2013\/02-xin.pdf (2013)","DOI":"10.1145\/2484425.2484427"},{"key":"27_CR84","doi-asserted-by":"publisher","unstructured":"Xin, R.S., Rosen, J., Zaharia, M., Franklin, M.J., Shenker, S., Stoica, I.: Shark: Sql and rich analytics at scale. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, ACM, New York, NY, USA, SIGMOD \u201913, pp. 13\u201324. doi: 10.1145\/2463676.2465288 (2013)","DOI":"10.1145\/2463676.2465288"},{"key":"27_CR85","doi-asserted-by":"crossref","unstructured":"Xin, R.S., Crankshaw, D., Dave, A., Gonzalez, J.E., Franklin, M.J., Stoica, I.: Graphx: Unifying data-parallel and graph-parallel analytics. CoRR arxiv:1402.2394 (2014)","DOI":"10.1145\/2484425.2484427"},{"key":"27_CR86","doi-asserted-by":"publisher","unstructured":"Yan, D., Cheng, J., Ozsu, M.T., Yang, F., Lu, Y., Lui, J.C.S., Zhang, Q., Ng,W.: A general-purpose query-centric framework for querying big graphs. Proc. VLDB Endow. 9(7), 564\u2013575 (2016). doi: 10.14778\/2904483.2904488","DOI":"10.14778\/2904483.2904488"},{"key":"27_CR87","doi-asserted-by":"crossref","unstructured":"Yu, J., Jinxuan, W., Mohamed, S.: GeoSpark: A Cluster Computing Framework for Processing Large-Scale Spatial Data. In: 23th International Conference on Advances in Geographic Information Systems. http:\/\/www.public.asu.edu\/~jinxuanw\/papers\/GeoSpark.pdf (2015)","DOI":"10.1145\/2820783.2820860"},{"key":"27_CR88","unstructured":"Yu, Y., Isard, M., Fetterly, D., Budiu, M., Erlingsson, U., Gunda, P.K., Currey, J.: Dryadlinq: A system for general-purpose distributed data-parallel computing using a high-level language. In: Proceedings of the 8th USENIX Conference on Operating Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, OSDI\u201908, pp. 1\u201314. http:\/\/dl.acm.org\/citation.cfm?id=1855741.1855742 (2008)"},{"key":"27_CR89","unstructured":"Zadeh, R.B., Meng, X., Yavuz, B., Staple, A., Pu, L., Venkataraman, S., Sparks, E., Ulanov, A., Zaharia, M.: linalg: Matrix computations in apache spark. arxiv:1509.02256 (2015)"},{"key":"27_CR90","doi-asserted-by":"crossref","DOI":"10.1145\/2886107","volume-title":"An Architecture for Fast and General Data Processing on Large Clusters","author":"M Zaharia","year":"2016","unstructured":"Zaharia, M.: An Architecture for Fast and General Data Processing on Large Clusters. Association for Computing Machinery, New York, NY, USA (2016)"},{"key":"27_CR91","unstructured":"Zaharia, M.: Spark 2.0. Presentation. http:\/\/www.slideshare.net\/databricks\/2016-spark-summit-east-keynote-matei-zaharia (2016)"},{"key":"27_CR92","unstructured":"Zaharia, M., Wendell, P.: Spark community update. Presentation. http:\/\/www.slideshare.net\/databricks\/spark-community-update-spark-summit-san-francisco-2015 (2015)"},{"key":"27_CR93","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets p\u00a010. http:\/\/dl.acm.org\/citation.cfm?id=1863103.1863113 (2010)"},{"key":"27_CR94","doi-asserted-by":"publisher","unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. NSDI\u201912 Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation pp. 2\u20132. doi: 10.1111\/j.1095-8649.2005.00662.x (2012)","DOI":"10.1111\/j.1095-8649.2005.00662.x"},{"key":"27_CR95","doi-asserted-by":"publisher","unstructured":"Zaharia, M., Das, T., Li, H., Hunter, T., Shenker, S., Stoica, I.: Discretized streams: fault-tolerant streaming computation at scale. In: Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles, ACM, New York, NY, USA, SOSP \u201913, pp. 423\u2013438. doi: 10.1145\/2517349.2522737 (2013)","DOI":"10.1145\/2517349.2522737"},{"key":"27_CR96","unstructured":"Zhang, Y., Jordan, M.I.: Splash: User-friendly programming interface for parallelizing stochastic algorithms. CoRR arXiv:1506.07552 (2015)"},{"key":"27_CR97","doi-asserted-by":"publisher","unstructured":"Zhao, G., Ling, C., Sun, D.: Sparksw: Scalable distributed computing system for large-scale biological sequence alignment. In: 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGrid 2015, Shenzhen, China, May 4\u20137, 2015, IEEE Computer Society, pp. 845\u2013852. doi: 10.1109\/CCGrid.2015.55 (2015)","DOI":"10.1109\/CCGrid.2015.55"},{"key":"27_CR98","doi-asserted-by":"crossref","unstructured":"Zhu, B., Mara, A., Mozo, A.: New Trends in Databases and Information Systems: ADBIS 2015 Short Papers and Workshops, BigDap, DCSA, GID, MEBIS, OAIS, SW4CH, WISARD, Poitiers, France, September 8\u201311, 2015. Proceedings, Springer International Publishing, Cham, chap CLUS: Parallel Subspace Clustering Algorithm on Spark, pp. 175\u2013185 (2015)","DOI":"10.1007\/978-3-319-23201-0_20"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-016-0027-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41060-016-0027-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-016-0027-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T12:27:40Z","timestamp":1692534460000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s41060-016-0027-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,13]]},"references-count":98,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2016,11]]}},"alternative-id":["27"],"URL":"https:\/\/doi.org\/10.1007\/s41060-016-0027-9","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10,13]]}}}