{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T02:14:46Z","timestamp":1767838486850,"version":"3.49.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,4,29]],"date-time":"2021-04-29T00:00:00Z","timestamp":1619654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,29]],"date-time":"2021-04-29T00:00:00Z","timestamp":1619654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The rise of unstructured data leads to unprecedented opportunities for marketing applications along with new methodological challenges to leverage such data. In particular, redundancy among the features extracted from this data deserves special attention as it might prevent current methods to benefit from it. In this study, we propose to investigate the value of multiple fine-grained data sources i.e. websurfing, use of applications and geospatial mobility for churn detection within telephone companies. This value is analysed both in substitution and in complement to the value of the well-known communication network. What is more, we also suggest an adaptation of the Random Forest algorithm called Essence Random Forest designed to better address redundancy among extracted features. Analysing fine-grained data of a telephone company, we first find that geo-spatial mobility data might be a good long term alternative to the classical communication network that might become obsolete due to the competition with digital communications. Then, we show that, on the short term, these alternative fine-grained data might complement the communication network for an improved churn detection. In addition, compared to Random Forest and Extremely Randomized Trees, Essence Random Forest better leverages the value of unstructured data by offering an enhanced churn detection regardless of the addressed perspective i.e. substitution or complement. Finally, Essence Random Forest converges faster to stable results which is a salient property in a resource constrained environment.<\/jats:p>","DOI":"10.1186\/s40537-021-00451-9","type":"journal-article","created":{"date-parts":[[2021,4,29]],"date-time":"2021-04-29T10:04:53Z","timestamp":1619690693000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Leveraging fine-grained mobile data for churn detection through Essence Random Forest"],"prefix":"10.1186","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0520-7364","authenticated-orcid":false,"given":"Christian","family":"Colot","sequence":"first","affiliation":[]},{"given":"Philippe","family":"Baecke","sequence":"additional","affiliation":[]},{"given":"Isabelle","family":"Linden","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,29]]},"reference":[{"key":"451_CR1","unstructured":"Coughlin T. 175 Zettabytes By 2025. https:\/\/www.forbes.com\/sites\/tomcoughlin\/2018\/11\/27\/175-zettabytes-by-2025\/"},{"issue":"6","key":"451_CR2","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1509\/jm.15.0413","volume":"80","author":"M Wedel","year":"2016","unstructured":"Wedel M, Kannan P. Marketing analytics for data-rich environments. J Market. 2016;80(6):97\u2013121.","journal-title":"J Market"},{"issue":"1","key":"451_CR3","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s10994-013-5375-2","volume":"95","author":"C Perlich","year":"2014","unstructured":"Perlich C, Dalessandro B, Raeder T, Stitelman O, Provost F. Machine learning for targeted display advertising: transfer learning in action. Mach Learn. 2014;95(1):103\u201327.","journal-title":"Mach Learn"},{"issue":"1","key":"451_CR4","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s40537-019-0180-9","volume":"6","author":"IM Al-Zuabi","year":"2019","unstructured":"Al-Zuabi IM, Jafar A, Aljoumaa K. Predicting customer\u2019s gender and age depending on mobile phone data. J Big Data. 2019;6(1):18.","journal-title":"J Big Data"},{"key":"451_CR5","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.eswa.2018.03.016","volume":"104","author":"J Lismont","year":"2018","unstructured":"Lismont J, Ram S, Vanthienen J, Lemahieu W, Baesens B. Predicting interpurchase time in a retail environment using customer-product networks: an empirical study and evaluation. Exp Syst Appl. 2018;104:22\u201332.","journal-title":"Exp Syst Appl"},{"key":"451_CR6","doi-asserted-by":"publisher","first-page":"4","DOI":"10.25300\/MISQ\/2016\/40.4.04","volume":"40","author":"D Martens","year":"2016","unstructured":"Martens D, Provost F, Clark J, de Fortuny EJ. Mining massive fine-grained behavior data to improve predictive analytics. MIS Q. 2016;40:4.","journal-title":"MIS Q"},{"issue":"1\u20132","key":"451_CR7","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s40547-017-0080-0","volume":"5","author":"E Ascarza","year":"2018","unstructured":"Ascarza E, Neslin SA, Netzer O, Anderson Z, Fader PS, Gupta S, Hardie BG, Lemmens A, Libai B, Neal D, et al. In pursuit of enhanced customer retention management: review, key issues, and future directions. Customer Needs Sol. 2018;5(1\u20132):65\u201381.","journal-title":"Customer Needs Sol"},{"issue":"2","key":"451_CR8","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s40171-019-00209-6","volume":"20","author":"M Farooq","year":"2019","unstructured":"Farooq M, Raju V. Impact of over-the-top (OTT) services on the telecom companies in the era of transformative marketing. Global J Flexible Syst Manag. 2019;20(2):177\u201388.","journal-title":"Global J Flexible Syst Manag"},{"issue":"7\u20138","key":"451_CR9","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1016\/j.telpol.2017.05.007","volume":"41","author":"C Stork","year":"2017","unstructured":"Stork C, Esselaar S, Chair C. OTT-Threat or opportunity for African Telcos? Telecommun Policy. 2017;41(7\u20138):600\u201316.","journal-title":"Telecommun Policy"},{"issue":"S4","key":"451_CR10","doi-asserted-by":"publisher","first-page":"145","DOI":"10.17485\/ijst\/2015\/v8iS4\/62238","volume":"8","author":"J Sujata","year":"2015","unstructured":"Sujata J, Sohag S, Tanu D, Chintan D, Shubham P, Sumit G. Impact of over the top (OTT) services on telecom service providers. Indian J Sci Technol. 2015;8(S4):145\u201360.","journal-title":"Indian J Sci Technol"},{"key":"451_CR11","first-page":"1","volume":"8","author":"C Colot","year":"2021","unstructured":"Colot C, Baecke P, Linden I. Alternatives for Telco Data Network: the value of spatial and referral networks for churn detection. Inf Syst Manag. 2021;8:1\u201319.","journal-title":"Inf Syst Manag"},{"issue":"1","key":"451_CR12","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.ejor.2015.05.030","volume":"247","author":"S Lessmann","year":"2015","unstructured":"Lessmann S, Baesens B, Seow H, Thomas L. Benchmarking state-of-the-art classification algorithms for credit scoring: a 10-year update. Eur J Operat Res. 2015;247(1):124\u201336.","journal-title":"Eur J Operat Res"},{"key":"451_CR13","unstructured":"Louppe G. Understanding random forests: From theory to practice. 2014; arXiv preprint arXiv:1407.7502"},{"issue":"2","key":"451_CR14","doi-asserted-by":"publisher","first-page":"2592","DOI":"10.1016\/j.eswa.2008.02.021","volume":"36","author":"EW Ngai","year":"2009","unstructured":"Ngai EW, Xiu L, Chau DC. Application of data mining techniques in customer relationship management: a literature review and classification. Exp Syst Appl. 2009;36(2):2592\u2013602.","journal-title":"Exp Syst Appl"},{"issue":"1","key":"451_CR15","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s40537-019-0191-6","volume":"6","author":"AK Ahmad","year":"2019","unstructured":"Ahmad AK, Jafar A, Aljoumaa K. Customer churn prediction in telecom using machine learning in big data platform. J Big Data. 2019;6(1):28\u201351.","journal-title":"J Big Data"},{"issue":"1","key":"451_CR16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s40537-019-0264-6","volume":"6","author":"NR Al-Molhem","year":"2019","unstructured":"Al-Molhem NR, Rahal Y, Dakkak M. Social network analysis in telecom data. J Big Data. 2019;6(1):99.","journal-title":"J Big Data"},{"issue":"1","key":"451_CR17","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45(1):5\u201332.","journal-title":"Mach Learn"},{"issue":"1","key":"451_CR18","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1039\/C2MB25327E","volume":"9","author":"Y-F Gao","year":"2013","unstructured":"Gao Y-F, Li B-Q, Cai Y-D, Feng K-Y, Li Z-D, Jiang Y. Prediction of active sites of enzymes by maximum relevance minimum redundancy (mrmr) feature selection. Mol BioSyst. 2013;9(1):61\u20139.","journal-title":"Mol BioSyst"},{"issue":"6","key":"451_CR19","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1016\/j.compeleceng.2012.09.001","volume":"38","author":"A Idris","year":"2012","unstructured":"Idris A, Rizwan M, Khan A. Churn prediction in telecom using random forest and PSO based data balancing in combination with various feature selection strategies. Comput Elect Eng. 2012;38(6):1808\u201319.","journal-title":"Comput Elect Eng"},{"key":"451_CR20","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.jtbi.2012.10.015","volume":"317","author":"KK Kandaswamy","year":"2013","unstructured":"Kandaswamy KK, Pugalenthi G, Kalies K-U, Hartmann E, Martinetz T. Ecmpred: Prediction of extracellular matrix proteins based on random forest with maximum relevance minimum redundancy feature selection. J Theor Biol. 2013;317:377\u201383.","journal-title":"J Theor Biol"},{"issue":"8","key":"451_CR21","doi-asserted-by":"publisher","first-page":"43927","DOI":"10.1371\/journal.pone.0043927","volume":"7","author":"B-Q Li","year":"2012","unstructured":"Li B-Q, Feng K-Y, Chen L, Huang T, Cai Y-D. Prediction of protein-protein interaction sites by random forest algorithm with MRMR and IFS. PloS ONE. 2012;7(8):43927.","journal-title":"PloS ONE"},{"issue":"2","key":"451_CR22","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1080\/07391102.2016.1138142","volume":"35","author":"L Liu","year":"2017","unstructured":"Liu L, Chen L, Zhang Y-H, Wei L, Cheng S, Kong X, Zheng M, Huang T, Cai Y-D. Analysis and prediction of drug-drug interaction by minimum redundancy maximum relevance and incremental feature selection. J Biomol Struct Dyn. 2017;35(2):312\u201329.","journal-title":"J Biomol Struct Dyn"},{"key":"451_CR23","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.jtbi.2014.06.037","volume":"360","author":"X Ma","year":"2014","unstructured":"Ma X, Sun X. Sequence-based predictor of atp-binding residues using random forest and MRMR-IFS feature selection. J Theor Biol. 2014;360:59\u201366.","journal-title":"J Theor Biol"},{"key":"451_CR24","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1155\/2015\/425810","volume":"2015","author":"X Ma","year":"2015","unstructured":"Ma X, Guo J, Sun X. Sequence-based prediction of RNA-binding proteins using random forest with minimum redundancy maximum relevance feature selection. BioMed Res Int. 2015;2015:78.","journal-title":"BioMed Res Int"},{"key":"451_CR25","doi-asserted-by":"crossref","unstructured":"Jan ZM, Verma B. Ensemble classifier optimization by reducing input features and base classifiers. In: 2019 IEEE congress on evolutionary computation (CEC). IEEE, 2019;1580\u20131587.","DOI":"10.1109\/CEC.2019.8790064"},{"issue":"18","key":"451_CR26","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1093\/bioinformatics\/btn356","volume":"24","author":"D Amaratunga","year":"2008","unstructured":"Amaratunga D, Cabrera J, Lee Y-S. Enriched random forests. Bioinformatics. 2008;24(18):2010\u20134.","journal-title":"Bioinformatics"},{"issue":"8","key":"451_CR27","first-page":"2446","volume":"13","author":"A Nagpal","year":"2018","unstructured":"Nagpal A, Singh V. Identification of significant features using random forest for high dimensional microarray data. J Eng Sci Technol. 2018;13(8):2446\u201363.","journal-title":"J Eng Sci Technol"},{"key":"451_CR28","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1155\/2015\/471371","volume":"2015","author":"T-T Nguyen","year":"2015","unstructured":"Nguyen T-T, Huang JZ, Nguyen TT. Unbiased feature selection in learning random forests for high-dimensional data. Sci World J. 2015;2015:7.","journal-title":"Sci World J"},{"issue":"4","key":"451_CR29","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1007\/s11634-018-0318-1","volume":"12","author":"Q Wang","year":"2018","unstructured":"Wang Q, Nguyen T-T, Huang JZ, Nguyen TT. An efficient random forests algorithm for high dimensional data classification. Adv Data Anal Classif. 2018;12(4):953\u201372.","journal-title":"Adv Data Anal Classif"},{"issue":"3","key":"451_CR30","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1109\/TNB.2012.2214232","volume":"11","author":"Q Wu","year":"2012","unstructured":"Wu Q, Ye Y, Liu Y, Ng MK. SNP selection and classification of genome-wide SNP data using stratified sampling random forests. IEEE Trans Nanobiosci. 2012;11(3):216\u201327.","journal-title":"IEEE Trans Nanobiosci"},{"issue":"2","key":"451_CR31","first-page":"44","volume":"8","author":"B Xu","year":"2012","unstructured":"Xu B, Huang JZ, Williams G, Wang Q, Ye Y. Classifying very high-dimensional data with random forests built from small subspaces. IJDWM. 2012;8(2):44\u201363.","journal-title":"IJDWM"},{"issue":"2","key":"451_CR32","doi-asserted-by":"publisher","first-page":"44","DOI":"10.4018\/jdwm.2012040103","volume":"8","author":"B Xu","year":"2012","unstructured":"Xu B, Huang JZ, Williams G, Ye Y. Hybrid weighted random forests for classifying very high-dimensional data. Int J Data Warehous Mining. 2012;8(2):44\u201363.","journal-title":"Int J Data Warehous Mining"},{"issue":"3","key":"451_CR33","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1016\/j.patcog.2012.09.005","volume":"46","author":"Y Ye","year":"2013","unstructured":"Ye Y, Wu Q, Huang JZ, Ng MK, Li X. Stratified sampling for feature subspace selection in random forests for high dimensional data. Pattern Recogn. 2013;46(3):769\u201387.","journal-title":"Pattern Recogn"},{"key":"451_CR34","doi-asserted-by":"crossref","unstructured":"Zhang Y, Cao G, Li X, Wang B. Cascaded random forest for hyperspectral image classification. In: IEEE journal of selected topics in applied earth observations and remote sensing. 2018;11(4):1082\u201394.","DOI":"10.1109\/JSTARS.2018.2809781"},{"key":"451_CR35","doi-asserted-by":"crossref","unstructured":"Kyrillidis A, Zouzias A. Non-uniform feature sampling for decision tree ensembles. In: 2014 IEEE international conference on acoustics, speech and signal processing. IEEE, 2014;4548\u20134552.","DOI":"10.1109\/ICASSP.2014.6854463"},{"issue":"10","key":"451_CR36","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1109\/TPAMI.2006.211","volume":"28","author":"JJ Rodriguez","year":"2006","unstructured":"Rodriguez JJ, Kuncheva LI, Alonso CJ. Rotation forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intellig. 2006;28(10):1619\u201330.","journal-title":"IEEE Trans Pattern Anal Mach Intellig"},{"issue":"10","key":"451_CR37","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1016\/j.patcog.2014.04.001","volume":"47","author":"L Zhang","year":"2014","unstructured":"Zhang L, Suganthan PN. Random forests with ensemble of feature spaces. Pattern Recogn. 2014;47(10):3429\u201337.","journal-title":"Pattern Recogn"},{"key":"451_CR38","doi-asserted-by":"crossref","unstructured":"Carreira-Perpi\u00f1\u00e1n M\u00c1, Zharmagambetov A. Ensembles of Bagged TAO Trees Consistently Improve over Random Forests, AdaBoost and Gradient Boosting. In: Proceedings of the 2020 ACM-IMS on foundations of data science conference, 2020; p 35\u201346","DOI":"10.1145\/3412815.3416882"},{"key":"451_CR39","doi-asserted-by":"crossref","unstructured":"Katuwal R, Suganthan PN, Zhang L. Heterogeneous oblique random forest. Pattern Recognition. 2020;99.","DOI":"10.1016\/j.patcog.2019.107078"},{"key":"451_CR40","doi-asserted-by":"crossref","unstructured":"Rastogi R, David A. Oblique Random Forest via Regularized Multisurface Proximal Support Vector Machine. In: 2019 Global conference for advancement in technology (GCAT). IEEE, 2019; p 1\u20136.","DOI":"10.1109\/GCAT47503.2019.8978384"},{"key":"451_CR41","doi-asserted-by":"crossref","unstructured":"Zhang L, Varadarajan J, Nagaratnam\u00a0Suganthan P, Ahuja N, Moulin P. textbfRobust visual tracking using oblique random forests. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017; p 5589\u201398","DOI":"10.1109\/CVPR.2017.617"},{"key":"451_CR42","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.eswa.2017.12.029","volume":"97","author":"J Abellan","year":"2018","unstructured":"Abellan J, Mantas CJ, Castellano JG, Moral-Garcia S. Increasing diversity in random forest learning algorithm via imprecise probabilities. Exp Syst Appl. 2018;97:228\u201343.","journal-title":"Exp Syst Appl"},{"issue":"21","key":"451_CR43","doi-asserted-by":"publisher","first-page":"10739","DOI":"10.1007\/s00500-018-3628-5","volume":"23","author":"CJ Mantas","year":"2019","unstructured":"Mantas CJ, Castellano JG, Moral-Garc\u00eda S, Abell\u00e1n J. A comparison of random forest based algorithms: random credal random forest versus oblique random forest. Soft Comput. 2019;23(21):10739\u201354.","journal-title":"Soft Comput"},{"issue":"1","key":"451_CR44","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006;63(1):3\u201342.","journal-title":"Mach Learn"},{"key":"451_CR45","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1109\/ACCESS.2017.2656618","volume":"5","author":"J Sun","year":"2017","unstructured":"Sun J, Zhong G, Dong J, Saeeda H, Zhang Q. Cooperative profit random forests with application in ocean front recognition. IEEE Access. 2017;5:1398\u2013408.","journal-title":"IEEE Access"},{"key":"451_CR46","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.neunet.2018.06.006","volume":"106","author":"J Sun","year":"2018","unstructured":"Sun J, Zhong G, Huang K, Dong J. Banzhaf random forests: cooperative game theory based random forests with consistency. Neural Netw. 2018;106:20\u20139.","journal-title":"Neural Netw"},{"key":"451_CR47","doi-asserted-by":"crossref","unstructured":"Zhang Y, Song B, Zhang Y, Chen S. An Advanced Random Forest Algorithm Targeting the Big Data with Redundant Features. In: International conference on algorithms and architectures for parallel processing. Springer, 2017; p 642\u201351.","DOI":"10.1007\/978-3-319-65482-9_49"},{"key":"451_CR48","unstructured":"Bernstein MN. Note on Random Forests. http:\/\/pages.cs.wisc.edu\/~lowmatthewb\/pages\/notes\/pdf\/ensembles\/RandomForests.pdf"},{"key":"451_CR49","unstructured":"SAS Institute Inc.: SAS\/STAT 15.1 User\u2019s Guide, 2018;"},{"issue":"2","key":"451_CR50","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1287\/mnsc.2014.1928","volume":"61","author":"L Ma","year":"2014","unstructured":"Ma L, Krishnan R, Montgomery AL. Latent homophily or social influence? an empirical analysis of purchase within a social network. Manag Sci. 2014;61(2):454\u201373.","journal-title":"Manag Sci"},{"key":"451_CR51","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1146\/annurev.soc.27.1.415","volume":"27","author":"M McPherson","year":"2001","unstructured":"McPherson M, Smith-Lovin L, Cook JM. Birds of a feather: homophily in social networks. Ann Rev Sociol. 2001;27:415\u201344.","journal-title":"Ann Rev Sociol"},{"key":"451_CR52","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1146\/annurev.psych.55.090902.142015","volume":"55","author":"RB Cialdini","year":"2004","unstructured":"Cialdini RB, Goldstein NJ. Social influence: compliance and conformity. Annu Rev Psychol. 2004;55:591\u2013621.","journal-title":"Annu Rev Psychol"},{"key":"451_CR53","unstructured":"Stankova M, Martens D, Provost F. Classification over bipartite graphs through projection 2015."},{"key":"451_CR54","doi-asserted-by":"crossref","unstructured":"De\u00a0Montjoye Y-., Quoidbach J, Robic F, Pentland A. Predicting Personality Using Novel Mobile Phone-based Metrics. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), vol. 7812 LNCS, 2013;48\u201355. Cited By :159. www.scopus.com","DOI":"10.1007\/978-3-642-37210-0_6"},{"issue":"2","key":"451_CR55","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1111\/j.1467-6494.1992.tb00970.x","volume":"60","author":"RR McCrae","year":"1992","unstructured":"McCrae RR, John OP. An introduction to the five-factor model and its applications. J Personal. 1992;60(2):175\u2013215.","journal-title":"J Personal"},{"key":"451_CR56","series-title":"Statistical challenges in astronomy","first-page":"243","volume-title":"Random forests: finding quasars","author":"L Breiman","year":"2003","unstructured":"Breiman L, Last M, Rice J. Random forests: finding quasars. Statistical challenges in astronomy. New York: Springer; 2003. p. 243\u201354."},{"key":"451_CR57","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"22","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;22:837\u201345.","journal-title":"Biometrics"},{"key":"451_CR58","unstructured":"Wertz J. Don't Spend 5 Times More Attracting New Customers, Nurture The Existing Ones. 2018. https:\/\/www.forbes.com\/sites\/jiawertz\/2018\/09\/12\/dont-spend-5-times-more-attracting-new-customers-nurture-the-existing-ones\/?sh=4a8dd4b25a8e"},{"issue":"1","key":"451_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-020-03822-w","volume":"21","author":"SR Zaim","year":"2020","unstructured":"Zaim SR, Kenost C, Berghout J, Chiu W, Wilson L, Zhang HH, Lussier YA. binomialRF: interpretable combinatoric efficiency of random forests to identify biomarker interactions. BMC Bioinf. 2020;21(1):1\u201322.","journal-title":"BMC Bioinf"},{"issue":"1","key":"451_CR60","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929\u201358.","journal-title":"J Mach Learn Res"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-021-00451-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-021-00451-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-021-00451-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T05:08:46Z","timestamp":1675228126000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-021-00451-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,29]]},"references-count":60,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["451"],"URL":"https:\/\/doi.org\/10.1186\/s40537-021-00451-9","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,29]]},"assertion":[{"value":"13 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"63"}}