{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:49:39Z","timestamp":1758980979623,"version":"3.41.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319943008"},{"type":"electronic","value":"9783319943015"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-94301-5_16","type":"book-chapter","created":{"date-parts":[[2018,6,20]],"date-time":"2018-06-20T16:37:59Z","timestamp":1529512679000},"page":"209-219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["On Scalability of Distributed Machine Learning with Big Data on Apache Spark"],"prefix":"10.1007","author":[{"given":"Ameen","family":"Abdel Hai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Babak","family":"Forouraghi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,21]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","unstructured":"Gupta, A., Thakur, H., Shrivastava, R., Kumar, P., Nag, S.: A big data analysis framework using apache spark and deep learning (2017). https:\/\/doi.org\/10.1109\/icdmw.2017.9","DOI":"10.1109\/icdmw.2017.9"},{"key":"16_CR2","unstructured":"Classification and Regression: Classification and Regression - Spark 2.2.0 Documentation. https:\/\/spark.apache.org\/docs\/2.2.0\/ml-classification-regression.html. Accessed 13 Mar 2018"},{"key":"16_CR3","unstructured":"Harnie, D., et al.: 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 871\u2013879. IEEE (2015). http:\/\/ieeexplore.ieee.org\/document\/7152571\/"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Miji, D., Varga, E., Member, S.: Machine Learning Driven Responsible Gaming Framework with Apache Spark, pp. 31\u201334 (2017)","DOI":"10.1109\/TELFOR.2017.8249466"},{"key":"16_CR5","unstructured":"Evaluation Metrics - RDD-based API. Evaluation Metrics - RDD-based API - Spark 2.2.0 Documentation. https:\/\/spark.apache.org\/docs\/2.2.0\/mllib-evaluation-metrics.html. Accessed 13 Mar 2018"},{"key":"16_CR6","unstructured":"Fire Department Calls for Service. Open Data of San Francisco. https:\/\/data.sfgov.org\/Public-Safety\/Fire-Department-Calls-for-Service\/nuek-vuh3. Accessed 7 Feb 2018"},{"key":"16_CR7","first-page":"167","volume":"34","author":"JH Friedman","year":"1997","unstructured":"Friedman, J.H.: Lazy decision trees. AAAI 34, 167\u2013180 (1997)","journal-title":"AAAI"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Berral-garc\u00eda, J.L.: A quick view on current techniques and machine learning algorithms for big data analytics. In: 18th International Conference on Transparent Optical Networks (ICTON), pp. 1\u20134 (2016)","DOI":"10.1109\/ICTON.2016.7550517"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Vimalkumar, K., Radhika, N.: A big data framework for intrusion detection, pp. 198\u2013204 (2017)","DOI":"10.1109\/ICACCI.2017.8125840"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Wang, K., Fu, J., Wang, K.: SPARK \u2013 a big data processing platform for machine learning. In: 2016 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration, pp. 48\u201351 (2016)","DOI":"10.1109\/ICIICII.2016.0023"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Capuccini, M., Carlsson, L., Norinder, U., Spjuth, O.: Proceedings of 2015 2nd IEEE\/ACM International Symposium on Big Data Computing, BDC 2015. Institute of Electrical and Electronics Engineers Inc., pp. 61\u201367 (2016)","DOI":"10.1109\/BDC.2015.35"},{"key":"16_CR12","unstructured":"Naribole, S.: H-1B Visa Petitions 2011\u20132016. In: H-1B Visa Petitions 2011\u20132016 | Kaggle (2017). https:\/\/www.kaggle.com\/nsharan\/h-1b-visa\/version\/2. Accessed 15 Mar 2018"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Alfred, R.: [Plenary Speaker] The Rise of Machine Learning for Big Data Analytics, 2016 (2016)","DOI":"10.1109\/ICSITech.2016.7852593"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Haupt, S.E., Kosovic, B.: Big data and machine learning for applied weather forecasts: Forecasting solar power for utility operations. In: Proceedings of 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015, pp. 496\u2013501 (2016)","DOI":"10.1109\/SSCI.2015.79"},{"issue":"5","key":"16_CR15","first-page":"1399","volume":"2","author":"S Mall","year":"2016","unstructured":"Mall, S., Rana, S.: Overview of big data and hadoop. Imperial J. Interdisc. Res. 2(5), 1399\u20131406 (2016)","journal-title":"Imperial J. Interdisc. Res."},{"key":"16_CR16","doi-asserted-by":"publisher","unstructured":"Biku, T., Rao, N., Akepogu, A.: Hadoop based feature selection and decision making models on big data. Indian J. Sci. Technol. 9(10) (2016). https:\/\/doi.org\/10.17485\/ijst\/2016\/v9i10\/88905","DOI":"10.17485\/ijst\/2016\/v9i10\/88905"},{"key":"16_CR17","unstructured":"Liu, T., Fang, Z., Zhao, C., Zhou, Y.: Proceedings of 2016 IEEE\/ACIS 15th International Conference on Computer and Information Science, ICIS 2016. Institute of Electrical and Electronics Engineers Inc. (2016)"},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Eluri, V., Ramesh, M., Al-Jabri, A., Jane, M.: A comparative study of various clustering techniques on big data sets using Apache Mahout. In: International Conference on Big Data and Smart City (ICBDSC), pp. 1\u20134 (2016). https:\/\/doi.org\/10.1109\/icbdsc.2016.7460397","DOI":"10.1109\/icbdsc.2016.7460397"}],"container-title":["Lecture Notes in Computer Science","Big Data \u2013 BigData 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-94301-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T06:54:43Z","timestamp":1751698483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-94301-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319943008","9783319943015"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-94301-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"21 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BIGDATA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bigdata2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.bigdatacongress.org\/2018\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"www.confhub.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"97","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":"22","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":"23% - 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","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":"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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}