{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T16:33:00Z","timestamp":1775493180496,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319729251","type":"print"},{"value":"9783319729268","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,12,21]],"date-time":"2017-12-21T00:00:00Z","timestamp":1513814400000},"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":[[2018]]},"DOI":"10.1007\/978-3-319-72926-8_23","type":"book-chapter","created":{"date-parts":[[2017,12,20]],"date-time":"2017-12-20T17:42:36Z","timestamp":1513791756000},"page":"268-285","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Data-Driven Machine Learning Approach for Predicting Missing Values in Large Data Sets: A Comparison Study"],"prefix":"10.1007","author":[{"given":"Ogerta","family":"Elezaj","sequence":"first","affiliation":[]},{"given":"Sule","family":"Yildirim","sequence":"additional","affiliation":[]},{"given":"Edlira","family":"Kalemi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,21]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Mannila, H.: Data mining: machine learning, statistics, and databases. In: 8th International Conference on Scientific and Statistical Database Management (SSDBM 1996), p. 2 (1996)","DOI":"10.1109\/SSDM.1996.505910"},{"key":"23_CR2","doi-asserted-by":"publisher","DOI":"10.1002\/0471725277","volume-title":"Survey Errors and Survey Costs","author":"RM Groves","year":"1989","unstructured":"Groves, R.M.: Survey Errors and Survey Costs. Wiley, New York (1989)"},{"key":"23_CR3","unstructured":"http:\/\/ec.europa.eu\/eurostat\/documents\/64157\/4372717\/Eurostat-Quality-Assurance-Framework-June-2013-ver-1-1-EN.pdf\/352234ca-77a0-47ca-93c7-d313d760bbd6"},{"key":"23_CR4","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1017\/S0021859600006912","volume":"20","author":"FG Allan","year":"1930","unstructured":"Allan, F.G., Wishart, J.: A method of estimating the yield of missing plot in field experiments. J. AgricSci. 20, 399\u2013406 (1930)","journal-title":"J. AgricSci."},{"key":"23_CR5","doi-asserted-by":"crossref","first-page":"137","DOI":"10.2307\/2983644","volume":"4","author":"MS Barlett","year":"1973","unstructured":"Barlett, M.S.: Some examples of statistical methods of research in agriculture and applied biology. J. R. Stat. Soc. B 4, 137\u2013185 (1973)","journal-title":"J. R. Stat. Soc. B"},{"key":"23_CR6","unstructured":"Berglund, P.A.: An Introduction to Multiple Imputation of Complex Sample Data using SAS\u00ae v9.2. SAS Global Forum 2010-Statistics and Data Analysis (2010)"},{"key":"23_CR7","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1093\/biomet\/63.3.581","volume":"63","author":"DB Rubin","year":"1976","unstructured":"Rubin, D.B.: Inference and missing data. Biometrika 63, 581\u2013592 (1976)","journal-title":"Biometrika"},{"key":"23_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316696","volume-title":"Multiple Imputation for Nonresponse in Surveys","author":"DB Rubin","year":"1987","unstructured":"Rubin, D.B.: Multiple Imputation for Nonresponse in Surveys. Wiley, New York (1987)"},{"key":"23_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/9781119013563","volume-title":"Statistical Analysis with Missing Data","author":"RJ Little","year":"2002","unstructured":"Little, R.J., Rubin, D.B.: Statistical Analysis with Missing Data, 2nd edn. Wiley, New York (2002)","edition":"2"},{"key":"23_CR10","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1175\/1520-0442(2001)014<0853:AOICDE>2.0.CO;2","volume":"14","author":"T Schneider","year":"2001","unstructured":"Schneider, T.: Analysis of incomplete climate data: estimation of mean values and covariance matrices and imputation of missing values. J. Clim. 14, 853\u2013871 (2001). American Meteorological Society","journal-title":"J. Clim."},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Di Zio, M., Scanu, M., Coppola, L., Luzi, O., Ponti, P.: Bayesian networks for imputation. J. R. Stat. Soc. Ser. A 167(2), 309\u2013322 (2004a)","DOI":"10.1046\/j.1467-985X.2003.00736.x"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Purwar, A., Singh, S.K.: Empirical evaluation of algorithms to impute missing values for financial dataset. IEEE (2014)","DOI":"10.1109\/ICICICT.2014.6781356"},{"key":"23_CR13","unstructured":"http:\/\/www.instat.gov.al\/en\/census\/census-2011.aspx"},{"key":"23_CR14","unstructured":"Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, vol. 2, pp. 1137\u20131143 (1995)"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Sun, G., Zhu, Y.: Data imbalance problem in text classification. In: 2010 Third International Symposium on Information Processing (ISIP). IEEE (2010)","DOI":"10.1109\/ISIP.2010.47"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Chawla, N.V., et al.: SMOTE: synthetic minority over-sampling technique. arXiv preprint arXiv:1106.1813 (2002)","DOI":"10.1613\/jair.953"},{"key":"23_CR17","unstructured":"Visa, S.: Fuzzy classifiers for imbalanced data sets. Department of Electrical and Computer Engineering and Computer Science, University of Cincinnati, Cincinnati (2006)"},{"key":"23_CR18","unstructured":"https:\/\/www.istat.it\/en\/tools\/methods-and-it-tools\/processing-tools\/concordjava"},{"key":"23_CR19","volume-title":"Data Mining: Concepts and Techniques","author":"J Han","year":"2001","unstructured":"Han, J., Kamber, M.: Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers, San Francisco (2001)"},{"issue":"1","key":"23_CR20","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1080\/14639220500284371","volume":"8","author":"Y Liu","year":"2007","unstructured":"Liu, Y., Salvendy, G.: Visualization support to better comprehend and improve decision tree classification modeling process: a survey and appraisal. Theor. Issues Ergon. Sci. 8(1), 63\u201392 (2007)","journal-title":"Theor. Issues Ergon. Sci."},{"key":"23_CR21","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/3-540-47887-6_54","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Y Fujikawa","year":"2002","unstructured":"Fujikawa, Y., Ho, T.B.: Cluster-based algorithms for dealing with missing values. In: Chen, M.-S., Yu, P.S., Liu, B. (eds.) PAKDD 2002. LNCS (LNAI), vol. 2336, pp. 549\u2013554. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-47887-6_54"},{"key":"23_CR22","unstructured":"Westin, L.: Missing data and the preprocessing perceptron. Department of Computing Science, Ume\u00e5 University (2002)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-72926-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T03:08:26Z","timestamp":1751166506000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-72926-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,21]]},"ISBN":["9783319729251","9783319729268"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-72926-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,21]]},"assertion":[{"value":"21 December 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Machine Learning, Optimization, and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Volterra","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.taosciences.it\/mod\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}