{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:43:21Z","timestamp":1757616201068,"version":"3.44.0"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"BUDDI AI","award":["RB1920CS200BUDD008156"],"award-info":[{"award-number":["RB1920CS200BUDD008156"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s41060-023-00441-5","type":"journal-article","created":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T11:05:13Z","timestamp":1692443113000},"page":"549-571","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CIAMS: clustering indices-based automatic classification model selection"],"prefix":"10.1007","volume":"20","author":[{"given":"Sudarsun","family":"Santhiappan","sequence":"first","affiliation":[]},{"given":"Nitin","family":"Shravan","sequence":"additional","affiliation":[]},{"given":"Balaraman","family":"Ravindran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"issue":"3","key":"441_CR1","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1023\/A:1021713901879","volume":"50","author":"PB Brazdil","year":"2003","unstructured":"Brazdil, P.B., Soares, C., Pinto da Costa, J.: Ranking learning algorithms: using IBL and meta-learning on accuracy and time results. Mach. Learn. 50(3), 251\u2013277 (2003)","journal-title":"Mach. Learn."},{"key":"441_CR2","doi-asserted-by":"publisher","unstructured":"Vainshtein, R., Greenstein-Messica, A., Katz, G., Shapira, B., Rokach, L.: A hybrid approach for automatic model recommendation. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, CIKM 2018, pp. 1623\u20131626. Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3269206.3269299","DOI":"10.1145\/3269206.3269299"},{"key":"441_CR3","doi-asserted-by":"publisher","unstructured":"Cohen-Shapira, N., Rokach, L., Shapira, B., Katz, G., Vainshtein, R.: Autogrd: model recommendation through graphical dataset representation. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 821\u2013830 (2019). https:\/\/doi.org\/10.1145\/3357384.3357896","DOI":"10.1145\/3357384.3357896"},{"key":"441_CR4","unstructured":"Drori, I., et al.: Automatic machine learning by pipeline synthesis using model-based reinforcement learning and a grammar. CoRR arXiv:1905.10345 (2019)"},{"key":"441_CR5","doi-asserted-by":"crossref","unstructured":"Thornton, C., Hutter, F., Hoos, H.H., Leyton-Brown, K.: Auto-weka: combined selection and hyperparameter optimization of classification algorithms. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 847\u2013855 (2013). arXiv:1208.3719","DOI":"10.1145\/2487575.2487629"},{"key":"441_CR6","unstructured":"Feurer, M., et al. In: Efficient and robust automated machine learning In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28, pp. 2962\u20132970. Curran Associates, Inc. (2015). http:\/\/papers.nips.cc\/paper\/5872-efficient-and-robust-automated-machine-learning.pdf"},{"key":"441_CR7","doi-asserted-by":"crossref","unstructured":"Olson, R., Moore, J.: TPOT: a tree-based pipeline optimization tool for automating machine learning. In: JMLR, pp. 151\u2013160 (2019)","DOI":"10.1007\/978-3-030-05318-5_8"},{"key":"441_CR8","doi-asserted-by":"crossref","unstructured":"Chen, B., Wu, H., Mo, W., Chattopadhyay, I., Lipson, H.: Autostacker: a compositional evolutionary learning system. CoRR arXiv:1803.00684 (2018)","DOI":"10.1145\/3205455.3205586"},{"key":"441_CR9","unstructured":"Real, E., Liang, C., So, D.R., Le, Q.V.: Automl-zero: evolving machine learning algorithms from scratch. arXiv:2003.03384 (2020)"},{"key":"441_CR10","unstructured":"Li, L., Jamieson, K.G., DeSalvo, G., Rostamizadeh, A., Talwalkar, A.: Efficient hyperparameter optimization and infinitely many armed bandits. arXiv:1603.06560 (2017)"},{"key":"441_CR11","unstructured":"Maechler, M., Rousseeuw, P., Struyf, A., Hubert, M., Hornik, K.: Cluster: cluster analysis basics and extensions. The Comprehensive R Archive Network (2019). R package version 2.0.8"},{"issue":"2","key":"441_CR12","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/s100440200009","volume":"5","author":"TK Ho","year":"2002","unstructured":"Ho, T.K.: A data complexity analysis of comparative advantages of decision forest constructors. Pattern Anal. Appl. 5(2), 102\u2013112 (2002). https:\/\/doi.org\/10.1007\/s100440200009","journal-title":"Pattern Anal. Appl."},{"key":"441_CR13","doi-asserted-by":"crossref","unstructured":"Das, P., et al.: Amazon sagemaker autopilot: a white box automl solution at scale (2020). arXiv:2012.08483","DOI":"10.1145\/3399579.3399870"},{"key":"441_CR14","doi-asserted-by":"publisher","unstructured":"Mishra, A. Amazon SageMaker, Ch. 16, pp. 353\u2013385. Wiley (2019). https:\/\/doi.org\/10.1002\/9781119556749.ch16","DOI":"10.1002\/9781119556749.ch16"},{"key":"441_CR15","unstructured":"LeDell, E., Poirier, S.: H2O AutoML: scalable automatic machine learning. In: 7th ICML Workshop on Automated Machine Learning (AutoML) (2020). https:\/\/www.automl.org\/wp-content\/uploads\/2020\/07\/AutoML_2020_paper_61.pdf"},{"key":"441_CR16","unstructured":"H2O.ai. H2O AutoML (2017). http:\/\/docs.h2o.ai\/h2o\/latest-stable\/h2o-docs\/automl.html. H2O version 3.30.0.1"},{"key":"441_CR17","unstructured":"Mukunthu, D., Shah, P., Tok, W.: Practical automated machine learning on Azure: using Azure machine learning to quickly build AI solutions. O\u2019Reilly Media, Incorporated 2019. https:\/\/books.google.co.in\/books?id=CgB4xgEACAAJ"},{"key":"441_CR18","unstructured":"Fusi, N., Sheth, R., Elibol, M.H.: Probabilistic matrix factorization for automated machine learning. NIPS 2018 (2018). https:\/\/www.microsoft.com\/en-us\/research\/publication\/probabilistic-matrix-factorization-for-automated-machine-learning\/. Preprint posted to Cornell University Library"},{"key":"441_CR19","unstructured":"Wang, C., Wu, Q., Weimer, M., Zhu, E.: Flaml: a fast and lightweight automl library. In: FLAML: a fast and lightweight AutoML library (2021)"},{"key":"441_CR20","unstructured":"Brazdil, P.B., Soares, C.: Ranking classification algorithms based on relevant performance information. In: Proceedings of the ECML-2000 Workshop on Meta-Learning: Building Automatic Advice Strategies for Model Selection and Method Combination. Springer, Berlin, Heidelberg (2000)"},{"key":"441_CR21","doi-asserted-by":"crossref","unstructured":"Poulakis, Y., Doulkeridis, C., Kyriazis, D.: A framework for automated clustering based on cluster validity indices. In: Proceedings of the 20th IEEE International Conference on Data Mining (2020). https:\/\/www.ds.unipi.gr\/prof\/cdoulk\/papers\/icdm20.pdf","DOI":"10.1109\/ICDM50108.2020.00153"},{"key":"441_CR22","doi-asserted-by":"publisher","unstructured":"Sahni, D., Pappu, S.J., Bhatt, N.: Aided selection of sampling methods for imbalanced data classification. In: 8th ACM IKDD CODS and 26th COMAD, pp. 198\u2013202 (2021). https:\/\/doi.org\/10.1145\/3430984.3431029","DOI":"10.1145\/3430984.3431029"},{"key":"441_CR23","doi-asserted-by":"publisher","unstructured":"Santhiappan, S., Shravan, N., Ravindran, B.: Is it hard to learn a classifier on this dataset? In: 8th ACM IKDD CODS and 26th COMAD, pp. 299\u2013306 (2021). https:\/\/doi.org\/10.1145\/3430984.3430997","DOI":"10.1145\/3430984.3430997"},{"key":"441_CR24","doi-asserted-by":"crossref","unstructured":"Katz, G., Shin, E.C.R., Song, D.X.: Explorekit: automatic feature generation and selection. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), pp. 979\u2013984 (2016)","DOI":"10.1109\/ICDM.2016.0123"},{"key":"441_CR25","unstructured":"Engels, R., Theusinger, C.: Using a data metric for preprocessing advice for data mining applications. In: Proceedings of the European Conference on Artificial Intelligence (ECAI-98), pp. 430\u2013434 (1998)"},{"key":"441_CR26","unstructured":"Li, L., Abu-Mostafa, Y.: Data complexity in machine learning. Caltech Computer Science Technical Report (2006)"},{"key":"441_CR27","unstructured":"Orriols-Puig, A., Maci\u00e0, N., Ho, T.: Dcol: data complexity library in c++ (documentation) (2010)"},{"key":"441_CR28","unstructured":"Mollineda, R.A., S\u00e1nchez, J.S., Sotoca, J.M.: Marques, J.S., P\u00e9rez de la Blanca, N., Pina, P. (eds.): Data characterization for effective prototype selection. In: Marques, J.S., P\u00e9rez de la Blanca, N., Pina, P. (eds.) Pattern Recognition and Image Analysis. Springer, Berlin, Heidelberg, pp. 27\u201334 (2005)"},{"key":"441_CR29","doi-asserted-by":"crossref","unstructured":"Peng, Y., Flach, P.A., Soares, C., Brazdil, P.: Improved dataset characterisation for meta-learning. In: Proceedings of the 5th International Conference on Discovery Science, pp. 141\u2013152 (2002)","DOI":"10.1007\/3-540-36182-0_14"},{"key":"441_CR30","unstructured":"Bensusan, H.: Odd bites into bananas don\u2019t make you blind: learning about simplicity and attribute addition. Tech. Rep., University of Bristol, GBR (1998)"},{"key":"441_CR31","unstructured":"Bensusan, H., Giraud-Carrier, C., Kennedy, C.: A higher-order approach to meta-learning. Tech. Rep., University of Bristol, GBR (2000)"},{"key":"441_CR32","doi-asserted-by":"crossref","unstructured":"Hoekstra, A., Duin, R.P.W.: On the nonlinearity of pattern classifiers. In: Proceedings of 13th International Conference on Pattern Recognition, vol. 4, pp. 271\u2013275 (1996)","DOI":"10.1109\/ICPR.1996.547429"},{"key":"441_CR33","doi-asserted-by":"crossref","unstructured":"Bensusan, H., Giraud-Carrier, C.: Discovering task neighbourhoods through landmark learning performances. In: Proceedings of the 4th European Conference on Principles and Practice of Knowledge Discovery in Databases, pp. 325\u2013330 (2000)","DOI":"10.1007\/3-540-45372-5_32"},{"key":"441_CR34","unstructured":"Pfahringer, B.: Meta-learning by landmarking various learning algorithms. In: Proceedings of the 17th International Conference on Machine Learning (2001)"},{"key":"441_CR35","unstructured":"F\u00fcrnkranz, J., Petrak, J., Giraud-Carrier, C., Lavrac, N., Moyle, S. Kavsek, B. (eds.): An evaluation of landmarking variants. In: Giraud-Carrier, C., Lavrac, N., Moyle, S. Kavsek, B. (eds.) Proceedings of the ECML\/PKDD Workshop on Integrating Aspects of Data Mining, Decision Support and Meta-Learning (IDDM-2001), pp. 57\u201368 (2001). http:\/\/tubiblio.ulb.tu-darmstadt.de\/51703\/"},{"key":"441_CR36","unstructured":"Petrak, J.: Fast subsampling performance estimates for classification algorithm selection. In: Proceedings of the ECML-00 Workshop on Meta-Learning: Building Automatic Advice Strategies for Model Selection and Method Combination, pp. 3\u201314 (2000)"},{"key":"441_CR37","doi-asserted-by":"publisher","unstructured":"Garcia, L.P., de Carvalho, A., Lorena, A.: Effect of label noise in the complexity of classification problems. Neurocomputing (2015). https:\/\/doi.org\/10.1016\/j.neucom.2014.10.085","DOI":"10.1016\/j.neucom.2014.10.085"},{"key":"441_CR38","doi-asserted-by":"publisher","unstructured":"Morais, G., Prati, R.: Complex network measures for data set characterization. In: Proceedings\u20142013 Brazilian Conference on Intelligent Systems, BRACIS 2013, pp. 12\u201318 (2013). https:\/\/doi.org\/10.1109\/BRACIS.2013.11","DOI":"10.1109\/BRACIS.2013.11"},{"key":"441_CR39","doi-asserted-by":"crossref","unstructured":"Z\u00f6ller, M.-A., Huber, M.F.: Benchmark and survey of automated machine learning frameworks (2021). arXiv:1904.12054","DOI":"10.1613\/jair.1.11854"},{"key":"441_CR40","doi-asserted-by":"publisher","unstructured":"Santu, S., et al.: Automl to date and beyond: Challenges and opportunities. ACM Comput. Surv. (2022). https:\/\/doi.org\/10.1145\/3470918. Publisher Copyright: $$\\copyright $$ 2021 Association for Computing Machinery","DOI":"10.1145\/3470918"},{"key":"441_CR41","doi-asserted-by":"crossref","unstructured":"He, X., Zhao, K., Chu, X.: Automl: a survey of the state-of-the-art (2021). arXiv:1908.00709","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"441_CR42","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"441_CR43","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1214\/aoms\/1177732979","volume":"2","author":"H Hotelling","year":"1931","unstructured":"Hotelling, H.: The generalization of Student\u2019s ratio. Ann. Math. Stat. 2(3), 360\u2013378 (1931). https:\/\/doi.org\/10.1214\/aoms\/1177732979","journal-title":"Ann. Math. Stat."},{"key":"441_CR44","unstructured":"Desgraupes, B.: Clustering indices. Tech. Rep., The Comprehensive R Archive Network (2013). https:\/\/cran.r-project.org\/web\/packages\/clusterCrit\/vignettes\/clusterCrit.pdf"},{"key":"441_CR45","unstructured":"Chen, T., Benesty, M., He, T.: Understand your dataset with XGBoost. XGBoost R package (2018)"},{"key":"441_CR46","unstructured":"Chernick, M.R., LaBudde, R.A.: An Introduction to Bootstrap Methods with Applications to R, 1st edn. Wiley Publishing (2011)"},{"key":"441_CR47","unstructured":"Bluman, A.G.: Elementary statistics: a step by step approach. McGraw-Hill Education, New York, NY, USA (2014)"},{"key":"441_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3347711","volume":"52","author":"A Lorena","year":"2019","unstructured":"Lorena, A., Garcia, L.P., Lehmann, J., de Souto, M., Ho, T.: How complex is your classification problem?: A survey on measuring classification complexity. ACM Comput. Surv. 52, 1\u201334 (2019). https:\/\/doi.org\/10.1145\/3347711","journal-title":"ACM Comput. Surv."},{"key":"441_CR49","doi-asserted-by":"crossref","unstructured":"Komorniczak, J., Ksieniewicz, P.: Problexity\u2014an open-source python library for binary classification problem complexity assessment (2022). arXiv:2207.06709","DOI":"10.1016\/j.neucom.2022.11.056"},{"key":"441_CR50","unstructured":"Alcoba\u00e7a, E., et al.: Mfe: Towards reproducible meta-feature extraction. J. Mach. Learn. Res. 21(111), 1\u20135 (2020). http:\/\/jmlr.org\/papers\/v21\/19-348.html"},{"key":"441_CR51","unstructured":"Alcoba\u00e7a, E., et al.: pymfe: python meta-feature extractor. https:\/\/github.com\/ealcobaca\/pymfe"},{"key":"441_CR52","unstructured":"Rosenberg, A., Hirschberg, J.: V-measure: a conditional entropy-based external cluster evaluation measure. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 410\u2013420 (2007). https:\/\/www.aclweb.org\/anthology\/D07-1043"},{"key":"441_CR53","doi-asserted-by":"publisher","unstructured":"Rao, C.R.: The utilization of multiple measurements in problems of biological classification. J. R. Stat. Soc.: Ser. B (Methodol.) 10(2), 159\u2013193 (1948). https:\/\/doi.org\/10.1111\/j.2517-6161.1948.tb00008.x","DOI":"10.1111\/j.2517-6161.1948.tb00008.x"},{"key":"441_CR54","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008). http:\/\/nlp.stanford.edu\/IR-book\/information-retrieval-book.html","DOI":"10.1017\/CBO9780511809071"},{"issue":"2","key":"441_CR55","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","volume":"PAMI\u20131","author":"DL Davies","year":"1979","unstructured":"Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. PAMI\u20131(2), 224\u2013227 (1979). https:\/\/doi.org\/10.1109\/TPAMI.1979.4766909","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"441_CR56","doi-asserted-by":"publisher","unstructured":"Rousseeuw, P., Rousseeuw, P.J.: Silhouettes: agraphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53\u201365 (1987). https:\/\/doi.org\/10.1016\/0377-0427(87)90125-7","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"441_CR57","doi-asserted-by":"publisher","unstructured":"Hubert, L., Schultz, J.: Quadratic assignment as a general data analysis strategy. Br. J. Math. Stat. Psychol. 29(2), 190\u2013241 (1976). https:\/\/doi.org\/10.1111\/j.2044-8317.1976.tb00714.x","DOI":"10.1111\/j.2044-8317.1976.tb00714.x"},{"key":"441_CR58","doi-asserted-by":"publisher","unstructured":"Dunn$$\\dagger $$, J. C. Well-separated clusters and optimal fuzzy partitions. Journal of Cybernetics 4(1), 95\u2013104 (1974). https:\/\/doi.org\/10.1080\/01969727408546059","DOI":"10.1080\/01969727408546059"},{"key":"441_CR59","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1111\/j.1365-2656.2008.01390.x","volume":"77","author":"J Elith","year":"2008","unstructured":"Elith, J., Leathwick, J., Hastie, T.: A working guide to boosted regression trees. J. Anim. Ecol. 77, 802\u2013813 (2008). https:\/\/doi.org\/10.1111\/j.1365-2656.2008.01390.x","journal-title":"J. Anim. Ecol."}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-023-00441-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-023-00441-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-023-00441-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T17:54:24Z","timestamp":1757094864000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-023-00441-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,19]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["441"],"URL":"https:\/\/doi.org\/10.1007\/s41060-023-00441-5","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"type":"print","value":"2364-415X"},{"type":"electronic","value":"2364-4168"}],"subject":[],"published":{"date-parts":[[2023,8,19]]},"assertion":[{"value":"24 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}