A SLR on Customer Dropout Prediction
Open accessThe DOI matches its Crossref record; 131 of the 132 references it cites were found in a registry or an index.
Abstract
Dropout prediction is a problem that is being addressed with machine learning algorithms; thus, appropriate approaches to address the dropout rate are needed. The selection of an algorithm to predict the dropout rate is only one problem to be addressed. Other aspects should also be considered, such as which features should be selected and how to measure accuracy while considering whether the features are appropriate according to the business context in which they are employed. To solve these questions, the goal of this paper is to develop a systematic literature review to evaluate the development of existing studies and to predict the dropout rate in contractual settings using machine learning to identify current trends and research opportunities. The results of this study identify trends in the use of machine learning algorithms in different business areas and in the adoption of machine learning algorithms, including which metrics are being adopted and what features are being applied. Finally, some research opportunities and gaps that could be explored in future research are presented.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Several systematic reviews using ASReview have already been published. For some examples, see [56-60].”
Citations
Cites
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · cited 1×
“The prediction should consider characteristics of the data such as class imbalance [60].”
BackgroundQuinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439 · cited 1×
“…machine learning, pattern recognition, database and data warehouse systems, information retrieval, visualization, algorithms, and high-performance computing [6] are employed to extract meaningful and useful information or patterns through automated or semiautomated methods [2], [3], [7].”
MethodLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
(1996) · Cited by 4,738
Systematic Reviews in the Social Sciences: A Practical Guide
Petticrew, M., & Roberts, H. (2006) · doi:10.1002/9780470754887 · Cited by 3,586
A few useful things to know about machine learning
Domingos, P. (2012) · Communications of the ACM · doi:10.1145/2347736.2347755 · Cited by 3,326 · cited 2×
“Machine learning extracts patterns from the data [37] by generalizing from the examples in the training set [38].”
MethodWeb of Science (WoS) and Scopus: The Titans of Bibliographic Information in Today’s Academic World
Pranckutė, R. (2021) · Publications · doi:10.3390/publications9010012 · Cited by 2,696
Conducting research literature reviews: from the Internet to paper
(2005) · Choice Reviews Online · doi:10.5860/choice.42-6198 · Cited by 1,854 · cited 1×
“According to Fink [56], systematic literature review (SLR) is a systematic, explicit, and reproducible method for identifying, evaluating, and synthesizing the existing body of completed and recorded work produced by researchers, scholars, and practitioners.”
BackgroundSwitching barriers and repurchase intentions in services
Jones, M. A., Mothersbaugh, D. L., & Beatty, S. E. (2000) · Journal of Retailing · doi:10.1016/s0022-4359(00)00024-5 · Cited by 1,571 · cited 1×
“These perspectives indicate that companies are realizing that their customer database is the most valuable asset that possess [10], [11].”
BackgroundData Mining Techniques: For Marketing, Sales, and Customer Relationship Management
Linoff, G. S., & Berry, M. J. (2004) · Cited by 1,232
A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning
Dargan, S., Kumar, M., Ayyagari, M. R., & Kumar, G. (2020) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-019-09344-w · Cited by 1,198
An open source machine learning framework for efficient and transparent systematic reviews
van de Schoot, R., de Bruin, J., Schram, R., Zahedi, P., de Boer, J., Weijdema, F., Kramer, B., Huijts, M., Hoogerwerf, M., Ferdinands, G., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-020-00287-7 · Cited by 1,157 · cited 3×
“The naive Bayes classifier was adopted using the following steps in ASReview: 1) Select five relevant and irrelevant articles; 2) ASReview orders the publications in such a way that the most relevant publications are listed first, simplifying the analysis of the abstracts; 3) All articles were screened, although the last…”
MethodLEARNING FROM CUSTOMER DEFECTIONS
Reichheld, F. F. (1996) · Cited by 789
Doing your literature review: traditional and systematic techniques
Cronin, C. (2011) · Evaluation & Research in Education · doi:10.1080/09500790.2011.581509 · Cited by 753
Modeling Customer Lifetime Value
Gupta, S., Hanssens, D., Hardie, B., Kahn, W., Kumar, V., Lin, N., Ravishanker, N., & Sriram, S. (2006) · Journal of Service Research · doi:10.1177/1094670506293810 · Cited by 724 · cited 1×
“There are two main scenarios, as follows [17], [18]: (1) contractual settings, where customers pay a fee, such as a subscription, and the customer informs the company that they are ending the relationship, and (2) noncontractual settings, for example, a customer buying a book, where a firm has to…”
BackgroundMarshall, I. J., & Wallace, B. C. (2019) · Systematic Reviews · doi:10.1186/s13643-019-1074-9 · Cited by 638 · cited 1×
“This process allowed the human reviewer to identify the studies to include earlier in the screening process [63].”
BackgroundCustomer Satisfaction Cues To Support Market Segmentation and Explain Switching Behavior
Athanassopoulos, A. D. (2000) · Journal of Business Research · doi:10.1016/s0148-2963(98)00060-5 · Cited by 629 · cited 1×
“These perspectives indicate that companies are realizing that their customer database is the most valuable asset that possess [10], [11].”
BackgroundKelleher, J. D., Namee, B. M., & D’Arcy, A. (2015) · Cited by 626
The Morgan Kaufmann Series in Data Management Systems
(2002) · Transactional Information Systems · doi:10.1016/b978-1-55860-508-4.50025-9 · Cited by 600
Defection detection: measuring and understanding the predictive accuracy of customer churn models
Neslin, S. A., Gupta, S., Kamakura, W., Lu, J., & Mason, C. H. (2006) · Journal of Marketing Research · doi:10.1509/jmkr.43.2.204 · Cited by 574 · cited 6×
“The problem is addressed in different organizations, such as the publishing, financial services, insurance, electric utilities, health care, banking, internet, telephone, and cable service industries [16].”
BackgroundInfluentialHandling class imbalance in customer churn prediction
Burez, J., & Van den Poel, D. (2009) · Expert Systems with Applications · doi:10.1016/j.eswa.2008.05.027 · Cited by 549 · cited 4×
“The main advantage in dropout is attributed to not placing more emphasis on one class over another class, meaning that it is not biased against the minority class [88] and that it is adopted to address the imbalance in the datasets [126].”
BackgroundMethodInfluentialApplying data mining to telecom churn management
Hung, S.-Y., Yen, D. C., & Wang, H.-Y. (2006) · Expert Systems with Applications · doi:10.1016/j.eswa.2005.09.080 · Cited by 514 · cited 5×
“The cluster category reflects the employment of approaches based on the adoption of unsupervised algorithms to develop the segmentation of customers, to support the use of machine learning algorithms to predict the churn in each segment [5], [25], [112].”
BackgroundMethodInfluentialVerbeke, W., Dejaeger, K., Martens, D., Hur, J., & Baesens, B. (2012) · European Journal of Operational Research · doi:10.1016/j.ejor.2011.09.031 · Cited by 462
Turning telecommunications call details to churn prediction: a data mining approach
Wei, C.-P., & Chiu, I.-T. (2002) · Expert Systems with Applications · doi:10.1016/s0957-4174(02)00030-1 · Cited by 460 · cited 3×
“The duration of the usage of a service could be measured in the days (or another time unit) between the contract starting date and the contract termination date [47].”
BackgroundMethodCoussement, K., & Van den Poel, D. (2008) · Expert Systems with Applications · doi:10.1016/j.eswa.2006.09.038 · Cited by 432 · cited 9×
“Several studies employed this technique by selecting different kernel functions, such as the radial basis function [95].”
BackgroundMethodInfluentialCustomer attrition analysis for financial services using proportional hazard models
Van den Poel, D., & Larivière, B. (2004) · European Journal of Operational Research · doi:10.1016/s0377-2217(03)00069-9 · Cited by 430 · cited 2×
“…supported statements [45]; (7) clusters to classify customers [69]; (8) survival analysis methods, which model the occurrence and timing of events [52]; (9) Markov chain [89]; (10) SVM, which classify the data using the maximal margin hyperplane [115]; and (11) other approaches not included in…”
Customer churn prediction using improved balanced random forests
Xie, Y., Li, X., Ngai, E. W. T., & Ying, W. (2009) · Expert Systems with Applications · doi:10.1016/j.eswa.2008.06.121 · Cited by 412 · cited 6×
“…be considered, such: (1) customers who have a greater risk of dropout should be targeted to gain a better ROI from the retention strategies [95], [123] and (2) the retention strategies should be developed by focusing on customers with higher satisfaction, or its inclusion could be a reminder of…”
BackgroundInfluentialBuilding comprehensible customer churn prediction models with advanced rule induction techniques
Verbeke, W., Martens, D., Mues, C., & Baesens, B. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2010.08.023 · Cited by 363 · cited 7×
“This metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77],”
BackgroundInfluentialA novel evolutionary data mining algorithm with applications to churn prediction
Au, W.-H., Chan, K. C. C., & Yao, X. (2003) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2003.819264 · Cited by 348 · cited 5×
“Between 2000 and 2008, only four studies were published: three studies were published in the telecommunications sector [5], [43], [47] and one study was published in the media business sector [89].”
BackgroundMethodInfluentialSurvival Analysis and Interpretation of Time-to-Event Data: The Tortoise and the Hare
Schober, P., & Vetter, T. R. (2018) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000003653 · Cited by 306 · cited 1×
“Survival Analysis consists of a set of methods to describe the probability of surviving past a specified time point, or more generally, the probability that the event of interest has not yet occurred by this time point [51], and attempts to address the timings”
MethodCustomer Behavior: Consumer Behavior and Beyond
Sheth, J. N., Mittal, B., & Newman, B. I. (1998) · Medical Entomology and Zoology · Cited by 295
Retention Futility: Targeting High-Risk Customers Might be Ineffective
Ascarza, E. (2018) · Journal of Marketing Research · doi:10.1509/jmr.16.0163 · Cited by 295 · cited 8×
“The general additive model was also explored, allowing us to relax in the assumptions that considered a nonparametric technique [91], and the general linear model [18] was also explored.”
BackgroundMethodInfluentialWhen Customers Are Members: Customer Retention in Paid Membership Contexts
Bhattacharya, C. B. (1998) · Journal of the Academy of Marketing Science · doi:10.1177/0092070398261004 · Cited by 285 · cited 1×
“Reichheld [30] evidenced that reducing dropout rates by 5% (e.g., from 15% per year to 10% per year) could represent an increase in profits up to double, as acquiring new customers costs 5 to 6 times more than retaining existing customers [31].”
BackgroundA Map of Threats to Validity of Systematic Literature Reviews in Software Engineering
Zhou, X., Jin, Y., Zhang, H., Li, S., & Huang, X. (2016) · 2016 23rd Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec.2016.031 · Cited by 260 · cited 1×
“common validity threats are listed as follows [133]: (1) construct validity; (2) internal validity; (3) external validity and (4) conclusion validity.”
BackgroundEdward, M., & Sahadev, S. (2011) · Asia Pacific Journal of Marketing and Logistics · doi:10.1108/13555851111143240 · Cited by 256 · cited 1×
“…switching from one company to a competitor in the near future, and, according to Verbeke et al. [13], is a management science problem that adopts a data mining approach to try to solve the problem related to the lower costs for retaining customers versus the costs of attracting new customers [14].”
BackgroundBurez, J., & Van den Poel, D. (2007) · Expert Systems with Applications · doi:10.1016/j.eswa.2005.11.037 · Cited by 241 · cited 4×
“The first viewpoint could be the importance and wider adoption of decision trees and random forests [49], [74], [89] and logistic regression [91], which could be attributed to its higher inter-pretability and flexibility [45].”
BackgroundInfluentialCredit card churn forecasting by logistic regression and decision tree
Nie, G., Rowe, W., Zhang, L., Tian, Y., & Shi, Y. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.06.028 · Cited by 223
Customer churn prediction in the telecommunication sector using a rough set approach
Amin, A., Anwar, S., Adnan, A., Nawaz, M., Alawfi, K., Hussain, A., & Huang, K. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.12.009 · Cited by 221
Coussement, K., Lessmann, S., & Verstraeten, G. (2017) · Decision Support Systems · doi:10.1016/j.dss.2016.11.007 · Cited by 212 · cited 10×
“…step [77], where a previously established process exists for extracting data, such as the Cross Industry Standard Process for Data Mining (CRISP-DM), which develops six distinct stages, i.e., business understanding, data understanding, data preprocessing, modeling, evaluation, and deployment [28].”
BackgroundMethodInfluentialCoussement, K., & Bock, K. W. D. (2013) · Journal of Business Research · doi:10.1016/j.jbusres.2012.12.008 · Cited by 198 · cited 7×
“Some studies identified algorithms such as CART [85], [93] or C4.”
BackgroundMethodInfluentialAn Overview of Predictive Learning and Function Approximation
Friedman, J. H. (1994) · From Statistics to Neural Networks · doi:10.1007/978-3-642-79119-2_1 · Cited by 189
Modeling churn using customer lifetime value
Glady, N., Baesens, B., & Croux, C. (2009) · European Journal of Operational Research · doi:10.1016/j.ejor.2008.06.027 · Cited by 187
Coussement, K., & den Poel, D. V. (2008) · Expert Systems with Applications · doi:10.1016/j.eswa.2008.07.021 · Cited by 179 · cited 7×
“and availability of logistic regression and its use as a benchmark against others were identified as advantages in several studies [32], [93].”
BackgroundMethodInfluentialImproved churn prediction in telecommunication industry using data mining techniques
Keramati, A., Jafari-Marandi, R., Aliannejadi, M., Ahmadian, I., Mozaffari, M., & Abbasi, U. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2014.08.041 · Cited by 176
Predictive Modeling With Big Data: Is Bigger Really Better ?
Junqué de Fortuny, E., Martens, D., & Provost, F. (2013) · Big Data · doi:10.1089/big.2013.0037 · Cited by 175 · cited 1×
“The data representing the behaviors of the customers should be considered, which allows improvement of the model performance if increased [131].”
BackgroundChurn prediction using comprehensible support vector machine: An analytical CRM application
Farquad, M. A. H., Ravi, V., & Raju, S. B. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2014.01.031 · Cited by 175 · cited 6×
“…different from ensemble methods uses several models that are built independently before developing a final step that combine different models to create a final class prediction; the approach applies a pipeline concept, where the output of one algorithm server as the input for another algorithm [108].”
BackgroundMethodInfluentialMaking Data Maximally Available
Hanson, B., Sugden, A., & Alberts, B. (2011) · Science · doi:10.1126/science.1203354 · Cited by 167 · cited 1×
“Considering that science is driven by data, with the development of new technologies, the increasing complexity of research and the amount of data collected, the challenge is to ensure that research is available to all [132].”
BackgroundSocial network analysis for customer churn prediction
Verbeke, W., Martens, D., & Baesens, B. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2013.09.017 · Cited by 164 · cited 2×
“Several studies adopted the lift [5], [15], [18], [43], [49], [54], [78], [80], [82], [89], [97], [118], [125] and accuracy considering that only 10% of customers are most likely to churn [8] in the studies [24], [28], [29], [42], [46], [90], [91], [93], [95], [123], [127].”
BackgroundEstimating Time to Conduct a Meta-analysis From Number of Citations Retrieved
Allen, I. E. (1999) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.282.7.634 · Cited by 163 · cited 1×
“…and retrieval of references, paper screening, data extraction and quality assessment, data entry, and tabulation, which according to Allen & Olkin [62] corresponds to approximately 51% of the time involved, we adopted a machine learning system that can estimate the probability that a document…”
MethodModel of Customer Churn Prediction on Support Vector Machine
XIA, G.-E., & JIN, W.-D. (2008) · Systems Engineering - Theory & Practice · doi:10.1016/s1874-8651(09)60003-x · Cited by 161 · cited 4×
“Other algorithms, such Bayesian classifier also included certain variants, such as: (1) naive Bayesian classifier [92], [110], [118], (2) naive Bayes tree [108], [109], [117], and (3) Bayesian belief network [101].”
BackgroundMethodInfluentialThe Morgan Kaufmann Series in Data Management Systems
(2006) · Elsevier eBooks · doi:10.1016/b978-1-55860-711-8.50025-3 · Cited by 156
Dynamic behavior based churn prediction in mobile telecom
Alboukaey, N., Joukhadar, A., & Ghneim, N. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113779 · Cited by 150 · cited 10×
“Higher interpretability allows us to solve the existing problem of a lack of causality [15], where the principle of Occam’s Razor, is usually interpreted to be simpler.”
BackgroundMethodInfluentialAn empirical evaluation of rotation-based ensemble classifiers for customer churn prediction
Bock, K. W. D., & den Poel, D. V. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.04.007 · Cited by 146 · cited 6×
“There are several algorithms that can be adopted [42]: logistic regression, artificial neural networks, survival analysis, Markov chains, support vector machines, generalized additive models, decision trees, naive Bayes classifiers, K-nearest neighbor classifiers, random forests, cost-sensitive…”
BackgroundMethodInfluentialDynamic classifier ensemble model for customer classification with imbalanced class distribution
Xiao, J., Xie, L., He, C., & Jiang, X. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.09.059 · Cited by 143 · cited 5×
“There are overlapping areas that target several business areas, such as the financial and telecom industries (6%) [9], [29], [46], [90], [122], financial and retail industries(3%) [68], [74], [97], financial, telecom and retail industries (1%) [42], and telecom and media industries (1%) [18].”
BackgroundMethodInfluentialAli, Ö. G., & Arıtürk, U. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.06.018 · Cited by 132
Variable selection by association rules for customer churn prediction of multimedia on demand
Tsai, C., & Chen, M.-Y. (2009) · Expert Systems with Applications · doi:10.1016/j.eswa.2009.06.076 · Cited by 128 · cited 4×
“The f-measure is calculated with the harmonic mean of recall and precision [15], [26], [45], [69], [72], [76], [96], [105], [107], [111], [112], [114], [121].”
MethodResultInfluentialA big data analytics model for customer churn prediction in the retiree segment
Shirazi, F., & Mohammadi, M. (2019) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2018.10.005 · Cited by 124
Prediction of Customer Attrition of Commercial Banks based on SVM Model
He, B., Shi, Y., Wan, Q., & Zhao, X. (2014) · Procedia Computer Science · doi:10.1016/j.procs.2014.05.286 · Cited by 123 · cited 3×
“…metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77], [82], [102], [111]–[113], [115].”
MethodResultCoussement, K., Benoit, D. F., & Van den Poel, D. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2009.07.029 · Cited by 117 · cited 3×
“The first viewpoint could be the importance and wider adoption of decision trees and random forests [49], [74], [89] and logistic regression [91], which could be attributed to its higher interpretability and flexibility [45].”
How to project customer retention
Fader, P. S., & Hardie, B. G. S. (2007) · Journal of Interactive Marketing · doi:10.1002/dir.20074 · Cited by 116 · cited 1×
“The main characteristic of a contractual setting is the interaction in which the customer ends the relationship [20].”
BackgroundCustomer event history for churn prediction: How long is long enough?
Ballings, M., & den Poel, D. V. (2012) · Expert Systems with Applications · doi:10.1016/j.eswa.2012.07.006 · Cited by 108
Customer Retention via Data Mining
Ng, K., & Liu, H. (2000) · Artificial Intelligence Review · doi:10.1023/a:1006676015154 · Cited by 105 · cited 1×
“Ng and Liu [44] suggested that deviations from normal patterns of behaviors are strong signs of likely defection, where deviation analysis is performed to detect customers who are at risk of dropout.”
BackgroundA Joint Model of Usage and Churn in Contractual Settings
Ascarza, E., & Hardie, B. G. S. (2013) · Marketing Science · doi:10.1287/mksc.2013.0786 · Cited by 102
Khodabandehlou, S., & Zivari Rahman, M. (2017) · Journal of Systems and Information Technology · doi:10.1108/jsit-10-2016-0061 · Cited by 102 · cited 1×
“…were applied by Verbeke et al. [50] However, certain studies did not identify the features employed [9], [12], [18], [22], [25], [42], [48], [67], [70], [73], [85], [87], [88], [97]–[99], [107], [110], [112], [113], [116], [119], [122], [127], which in some cases are related to the usage of…”
MethodDelen, D., Topuz, K., & Eryarsoy, E. (2019) · European Journal of Operational Research · doi:10.1016/j.ejor.2019.03.037 · Cited by 100
Idris, A., Khan, A., & Lee, Y. S. (2013) · Applied Intelligence · doi:10.1007/s10489-013-0440-x · Cited by 99 · cited 6×
“This metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77],”
BackgroundMethodInfluentialChurn Prediction in Mobile Social Games: Towards a Complete Assessment Using Survival Ensembles
Perianez, A., Saas, A., Guitart, A., & Magne, C. (2016) · 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2016.84 · Cited by 97 · cited 6×
“Perianez et al. [92] approached this problem using survival analysis, with the goal to determine not only if a customer will dropout but also when dropout would occur.”
BackgroundMethodResultInfluentialIntelligent data analysis approaches to churn as a business problem: a survey
García, D. L., Nebot, À., & Vellido, A. (2016) · Knowledge and Information Systems · doi:10.1007/s10115-016-0995-z · Cited by 96 · cited 6×
“…retention strategy, and helpdesk interactions, were applied by Verbeke et al. [50] However, certain studies did not identify the features employed [9], [12], [18], [22], [25], [42], [48], [67], [70], [73], [85], [87], [88], [97]–[99], [107], [110], [112], [113], [116], [119], [122], [127], which…”
BackgroundInfluentialStaying Power of Churn Prediction Models
Risselada, H., Verhoef, P. C., & Bijmolt, T. H. A. (2010) · Journal of Interactive Marketing · doi:10.1016/j.intmar.2010.04.002 · Cited by 92 · cited 7×
“There are overlapping areas that target several business areas, such as the financial and telecom industries (6%) [9], [29], [46], [90], [122], financial and retail industries(3%) [68], [74], [97], financial, telecom and retail industries (1%) [42], and telecom and media industries (1%) [18].”
BackgroundMethodInfluentialWhy you should stop predicting customer churn and start using uplift models
Devriendt, F., Berrevoets, J., & Verbeke, W. (2021) · Information Sciences · doi:10.1016/j.ins.2019.12.075 · Cited by 90 · cited 10×
“This perspective could be realized by predicting two possible events, either dropout or nondropout, which allow us to identify ways to induce customers to stay [16] by estimating the probability of customer churning in an given eperiod of time [33].”
BackgroundInfluentialMoeyersoms, J., & Martens, D. (2015) · Decision Support Systems · doi:10.1016/j.dss.2015.02.007 · Cited by 89 · cited 5×
“The availability of behavioral data (such as those represented in the time series) allows us to improve the model performance [82] and complement the information existing in the form of structured data (e.g., sociodemographic data).”
BackgroundResultInfluentialBock, K. W. D., & den Poel, D. V. (2012) · Expert Systems with Applications · doi:10.1016/j.eswa.2012.01.014 · Cited by 82 · cited 6×
“[46].”
BackgroundMethodInfluentialImproving customer retention in financial services using kinship network information
Benoit, D. F., & den Poel, D. V. (2012) · Expert Systems with Applications · doi:10.1016/j.eswa.2012.04.016 · Cited by 79 · cited 5×
“The first viewpoint could be the importance and wider adoption of decision trees and random forests [49], [74], [89] and logistic regression [91], which could be attributed to its higher interpretability and flexibility [45].”
BackgroundInfluentialPredicting customer churn through interpersonal influence
Zhang, X., Zhu, J., Xu, S., & Wan, Y. (2011) · Knowledge-Based Systems · doi:10.1016/j.knosys.2011.12.005 · Cited by 78
Burez, J., & den Poel, D. V. (2007) · Expert Systems with Applications · doi:10.1016/j.eswa.2007.07.036 · Cited by 78 · cited 11×
“The idea was clarified by Burez and Vandenpoel [86] by identifying a static approach, where churn behavior was predicted at a moment in time using random forest and dynamic approaches over a period of time.”
BackgroundMethodInfluentialBig Data, Predictive Analytics and Machine Learning
Ongsulee, P., Chotchaung, V., Bamrungsi, E., & Rodcheewit, T. (2018) · International Conference on ICT and Knowledge Engineering · doi:10.1109/ictke.2018.8612393 · Cited by 77 · cited 1×
“…after the emergence of the fields of artifi-cial intelligence (machine learning) [35], machine learning is considered a modern extension of predictive analytics [36], understood as an automated process to extract patterns from the data [37] generalizing from the examples in the training set [38].”
MethodDierkes, T., Bichler, M., & Krishnan, R. (2011) · Decision Support Systems · doi:10.1016/j.dss.2011.01.002 · Cited by 76 · cited 4×
“This metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77], [82], [102], [111]–[113],…”
ResultInfluentialA churn prediction model for prepaid customers in telecom using fuzzy classifiers
Azeem, M., Usman, M., & Fong, A. C. M. (2017) · Telecommunication Systems · doi:10.1007/s11235-017-0310-7 · Cited by 75 · cited 10×
“approaches, such as (1) AdaBoost [77], [97], [99], [106], [116], [121]; (2) gradient boosting [28]; and (3) extreme gradient boosting [90].”
BackgroundMethodInfluentialVijaya, J., & Sivasankar, E. (2017) · Cluster Computing · doi:10.1007/s10586-017-1172-1 · Cited by 74 · cited 9×
“Vijaya and Sivasankar [112] suggested that works that adopt hybrid models combining more than one classifier can achieve increased performance compared with those using single classifiers.”
BackgroundMethodResultInfluentialCustomer Churn Prediction Modelling Based on Behavioural Patterns Analysis using Deep Learning
Agrawal, S., Das, A., Gaikwad, A. K., & Dhage, S. (2018) · International Conference on Smart Computing and Electronic Enterprise (ICSCEE) · doi:10.1109/icscee.2018.8538420 · Cited by 69 · cited 4×
“…were adopted: (1) counterpropagation neural networks [85] and multilayer perceptron [28], [50], [77], [115], [121]; (2) extreme learning machines [40], [84]; (3) long short term memory [15]; (4) convolutional neural networks [15]; (5) multilayer perceptron [28], [50], [77], [115], [121]; (6)…”
BackgroundMethodInfluentialBehavioral attributes and financial churn prediction
Kaya, E., Dong, X., Suhara, Y., Balcisoy, S. S., Bozkaya, B., & Pentland, A. (2018) · EPJ Data Science · doi:10.1140/epjds/s13688-018-0165-5 · Cited by 66 · cited 2×
“The main advantage in dropout is attributed to not placing more emphasis on one class over another class, meaning that it is not biased against the minority class [88] and that it is adopted to address the imbalance in the datasets [126].”
BackgroundBenchmarking sampling techniques for imbalance learning in churn prediction
Zhu, B., Baesens, B., Backiel, A., & Broucke, S. V. (2017) · Journal of the Operational Research Society · doi:10.1057/s41274-016-0176-1 · Cited by 63
Feature-selection-based dynamic transfer ensemble model for customer churn prediction
Xiao, J., Xiao, Y., Huang, A., Liu, D., & Wang, S. (2014) · Knowledge and Information Systems · doi:10.1007/s10115-013-0722-y · Cited by 61 · cited 5×
“…using the ratio between the total number of correct predictions and the total number of predictions and has been widely employed in several studies [25], [26], [40], [45], [46], [54], [69], [71], [72], [76], [85], [98], [101], [103]–[105], [108], [109], [111]–[118], [118], [120]–[122], [124].”
BackgroundMethodInfluentialForecasting client retention — A machine-learning approach
Schaeffer, S. E., & Sanchez, S. V. R. (2019) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2019.101918 · Cited by 60 · cited 4×
“More recently, in 2017, fuzzy classifiers [77] were applied, and random walk [75] and multivariate time series [15], [99] were utilized in studies published in 2020.”
BackgroundMethodInfluentialApplying CHAID for logistic regression diagnostics and classification accuracy improvement
Antipov, E. A., & Pokryshevskaya, E. B. (2010) · Journal of Targeting Measurement and Analysis for Marketing · doi:10.1057/jt.2010.3 · Cited by 59
ggRandomForests: Exploring Random Forest SurvivalPreprint
Ehrlinger, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.08974 · Cited by 57 · cited 1×
“More recent machine learning algorithms for survival analysis provide additional advantages that sur-pass the existing limitations, such as Cox proportional hazard assumptions [53], and allow the use of time-dependent variables.”
BackgroundOn the operational efficiency of different feature types for telco Churn prediction
Mitrović, S., Baesens, B., Lemahieu, W., & Weerdt, J. D. (2017) · European Journal of Operational Research · doi:10.1016/j.ejor.2017.12.015 · Cited by 50 · cited 1×
“Several studies adopted the lift [5], [15], [18], [43], [49], [54], [78], [80], [82], [89], [97], [118], [125] and accuracy considering that only 10% of customers are most likely to churn [8] in the studies [24], [28], [29], [42], [46], [90], [91], [93], [95], [123], [127].”
BackgroundProfit optimizing customer churn prediction with Bayesian network classifiers
Verbraken, T., Verbeke, W., & Baesens, B. (2014) · Intelligent Data Analysis · doi:10.3233/ida-130625 · Cited by 49 · cited 4×
“Other algorithms, such Bayesian classifier also included certain variants, such as: (1) naive Bayesian classifier [92], [110], [118], (2) naive Bayes tree [108], [109], [117], and (3) Bayesian belief network [101].”
BackgroundMethodInfluentialA customer lifetime value model for the banking industry: a guide to marketing actions
Ekinci, Y., Uray, N., & Ülengin, F. (2014) · European Journal of Marketing · doi:10.1108/ejm-12-2011-0714 · Cited by 48
Farquad, M. A. H., Ravi, V., & Bapi, R. S. (2012) · International Journal of Electronic Customer Relationship Management · doi:10.1504/ijecrm.2012.046470 · Cited by 47 · cited 4×
“Other algorithms, such Bayesian classifier also included certain variants, such as: (1) naive Bayesian classifier [92], [110], [118], (2) naive Bayes tree [108], [109], [117], and (3) Bayesian belief network [101].”
BackgroundMethodInfluentialSivasankar, E., & Vijaya, J. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3548-4 · Cited by 43
Customer Churn Prediction for Broadband Internet Services
Huang, B. Q., Kechadi, T., & Buckley, B. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03730-6_19 · Cited by 41 · cited 3×
“including artificial neural networks, fuzzy systems, evolutionary computing, and swarm intelligence; (2) ensemble, which use multiple classifiers that are built independently and that participate in a voting procedure to obtain a final class prediction, such as random forests, bagging and boosting [50]; (3) decision t…”
BackgroundMethodEstimating customer churn under competing risks
Routh, P., Roy, A., & Meyer, J. (2020) · Journal of the Operational Research Society · doi:10.1080/01605682.2020.1776166 · Cited by 39 · cited 6×
“Precision indicates the fraction of the detected class members that are actually correct [69]; and was adopted in the studies [25], [26], [45], [69], [72], [75], [76], [82], [96], [103], [105], [107], [111], [112], [114], [121].”
MethodResultInfluentialSocial network analysis in Telecom data
Al-Molhem, N. R., Rahhal, Y., & Dakkak, M. (2019) · Journal Of Big Data · doi:10.1186/s40537-019-0264-6 · Cited by 35 · cited 2×
“[68], [74], [97], financial, telecom and retail industries (1”
BackgroundCalling communities analysis and identification using machine learning techniques
Kianmehr, K., & Alhajj, R. (2008) · Expert Systems with Applications · doi:10.1016/j.eswa.2008.07.072 · Cited by 30 · cited 5×
“This metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77],”
MethodResultInfluentialThe Importance of Social Embeddedness: Churn Models at Mobile Providers
Benedek, G., Lublóy, Á., & Vastag, G. (2014) · Decision Sciences · doi:10.1111/deci.12057 · Cited by 27 · cited 1×
“[83] employed network topological properties to represent whether the calls were made to customers within the same telecommunication service or to a customer using another telecommunication service.”
MethodMicro- and macro-level churn analysis of large-scale mobile games
Liu, X., Xie, M., Wen, X., Chen, R., Ge, Y., Duffield, N. G., & Wang, N. (2019) · Knowledge and Information Systems · doi:10.1007/s10115-019-01394-7 · Cited by 26 · cited 5×
“Precision indicates the fraction of the detected class members that are actually correct [69]; and was adopted in the studies [25], [26], [45], [69], [72], [75], [76], [82], [96], [103], [105], [107], [111], [112], [114], [121].”
BackgroundMethodResultInfluentialForsman, J., van den Bogaard, M., Linder, C., & Fraser, D. (2014) · European Journal of Engineering Education · doi:10.1080/03043797.2014.941340 · Cited by 23 · cited 1×
“Certain areas only addressed the subject in 2020, such as logistics [99], hospitality [96] and education [101]; however, the problem was addressed using traditional statistical methods without machine learning approaches [128].”
Lee, K. C., & Jo, N. Y. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-17569-5_30 · Cited by 21 · cited 1×
“The accuracy is calculated using the ratio between the total number of correct predictions and the total number of predictions and has been widely employed in several studies [25], [26], [40], [45], [46], [54], [69], [71], [72], [76], [85], [98], [101], [103]–[105], [108], [109], [111]–[118], [118], [120]–[122], [124].”
MethodChurn Prediction in Banking System using K-Means, LOF, and CBLOF
Ullah, I., Hussain, H., Ali, I., & Liaquat, A. (2019) · International Conference on Electrical, Communication, and Computer Engineering (ICECCE) · doi:10.1109/icecce47252.2019.8940667 · Cited by 21 · cited 6×
“Ullah et al. [107] also employed clustering by employing fuzzy c-means, possibility c-means and possibility fuzzy c-means.”
BackgroundMethodResultInfluentialProfit-Based Model Selection for Customer Retention Using Individual Customer Lifetime Values
Óskarsdóttir, M., Baesens, B., & Vanthienen, J. (2018) · Big Data · doi:10.1089/big.2018.0015 · Cited by 20 · cited 3×
“There are overlapping areas that target several business areas, such as the financial and telecom industries (6%) [9], [29], [46], [90], [122], financial and retail industries(3%) [68], [74], [97], financial, telecom and retail industries (1%) [42], and telecom and media industries (1%) [18].”
BackgroundMethodData Mining Using Rules Extracted from SVM: An Application to Churn Prediction in Bank Credit Cards
Farquad, M. A. H., Ravi, V., & Bapi, R. S. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10646-0_47 · Cited by 19 · cited 2×
“Other works employed specificity [85], [104], [106], [108], [109], [117], [119], which is also identified as the true negative [111], [112], and represent the true negative rate by measuring the proportion of non-churners that are correctly classified [50].”
BackgroundChurn perdiction in the telecom business
Georgina, E., & Mendes‐Moreira, J. (2016) · International Conference on Digital Information Management · doi:10.1109/icdim.2016.7829775 · Cited by 19 · cited 7×
“approaches, such as (1) AdaBoost [77], [97], [99], [106], [116], [121]; (2) gradient boosting [28]; and (3) extreme gradient boosting [90].”
BackgroundMethodInfluentialJafari-Marandi, R., Denton, J., Idris, A., Smith, B. K., & Keramati, A. (2020) · Neural computing & applications (Print) · doi:10.1007/s00521-020-04850-6 · Cited by 19
A Graph-Based Churn Prediction Model for Mobile Telecom Networks
Saravanan, M., & Raajaa, G. S. V. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35527-1_31 · Cited by 18 · cited 1×
“The accuracy is calculated using the ratio between the total number of correct predictions and the total number of predictions and has been widely employed in several studies [25], [26], [40], [45], [46], [54], [69], [71], [72], [76], [85], [98], [101], [103]–[105], [108], [109], [111]–[118], [118], [120]–[122], [124].”
MethodThe Rationale Behind Seeking Inspiration from Nature
Steer, K. C. B., Wirth, A., & Halgamuge, S. K. (2009) · Studies in computational intelligence · doi:10.1007/978-3-642-00267-0_2 · Cited by 17
Applicability of Customer Churn Forecasts in a Non-Contractual Setting
Hopmann, J., & Thede, A. (2005) · Springer eBooks · doi:10.1007/3-540-26981-9_38 · Cited by 17 · cited 1×
“Depending on the contractual relationships and the knowledge of the exact time of churn, contracts are not fully applicable in the context of catalog retailers or other non-membership businesses [23]; moreover, contractual settings provide subscription records and usage logs [24].”
BackgroundApplying Fuzzy Data Mining to Telecom Churn Management
Liao, K.-H., & Chueh, H.-E. (2010) · Communications in computer and information science · doi:10.1007/978-3-642-18129-0_41 · Cited by 15 · cited 1×
“…applied by Verbeke et al. [50] However, certain studies did not identify the features employed [9], [12], [18], [22], [25], [42], [48], [67], [70], [73], [85], [87], [88], [97]–[99], [107], [110], [112], [113], [116], [119], [122], [127], which in some cases are related to the usage of more than…”
BackgroundEnsembles of Probability Estimation Trees for Customer Churn Prediction
Bock, K. W. D., & den Poel, D. V. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13025-0_7 · Cited by 13 · cited 7×
“approaches, such as (1) AdaBoost [77], [97], [99], [106], [116], [121]; (2) gradient boosting [28]; and (3) extreme gradient boosting [90].”
BackgroundMethodInfluentialNature-Inspired Algorithms for Real-World Optimization Problems
Fang, W. H., Li, X., Zhang, M., & Hu, M. (2015) · Journal of Applied Mathematics · doi:10.1155/2015/359203 · Cited by 13 · cited 2×
“Algorithms that are inspired by nature [129], [130] include neural networks, fuzzy systems, evolutionary computing, and swarm intelligence [129].”
BackgroundMethodChurn prediction model for effective gym customer retention
Šemrl, J., & Matei, A. (2017) · doi:10.1109/besc.2017.8256385 · Cited by 13
Applicability of machine-learning techniques in predicting customer defection
Martono, N. P., & Ohwada, H. (2014) · International Symposium on Technology Management and Emerging Technologies (ISTMET) · doi:10.1109/istmet.2014.6936498 · Cited by 12 · cited 2×
“The customer must choose whether to opt-in or to opt-out [22], i.e., (1) customers will choose to opt-in if they want to enter into a contract with a particular form (e.g., renewal form) or (2) customers will choose to opt-out if they prefer not to renew.”
BackgroundMohanty, R., & Rani, K. J. (2015) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn.2015.123 · Cited by 12 · cited 7×
“This metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77], [82], [102], [111]–[113],…”
BackgroundMethodInfluentialImproving Customer Churn Prediction by Data Augmentation Using Pictorial Stimulus-Choice Data
Ballings, M., den Poel, D. V., & Verhagen, E. (2012) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-30864-2_21 · Cited by 11 · cited 2×
“[81] explored the use of pictorial data to represent feelings andmindset, which represent variables that cannot be extracted from internal processes within the organization, such as purchase intentions, interests, satisfaction,”
BackgroundCustomer Churn Models: A Comparison of Probability and Data Mining Approaches
Tamaddoni, A., Stakhovych, S., & Ewing, M. T. (2015) · Developments in marketing science: proceedings of the Academy of Marketing Science · doi:10.1007/978-3-319-24184-5_35 · Cited by 10
Scalable RFM-enriched Representation Learning for Churn Prediction
Mitrović, S., Singh, G., Baesens, B., Lemahieu, W., & Weerdt, J. D. (2017) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2017.42 · Cited by 10 · cited 2×
“Other studies addressed the problem using Recency, Frequency, and Monetary (RFM) model generated variables [32], [80], [93].”
BackgroundMethodFarquad, M. A. H., Ravi, V., & Bapi, R. S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15387-7_50 · Cited by 9
Amornvetchayakul, P., & Phumchusri, N. (2020) · IEEE International Conference on Industrial Engineering and Applications (ICIEA) · doi:10.1109/iciea49774.2020.9102099 · Cited by 9 · cited 4×
“…metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77], [82], [102], [111]–[113], [115].”
MethodResultInfluentialTransfer Ensemble Model for Customer Churn Prediction with Imbalanced Class Distribution
Wang, Y., & Xiao, J. (2011) · International Conference of Information Technology, Computer Engineering and Management Sciences · doi:10.1109/icm.2011.397 · Cited by 8 · cited 4×
“This metric was referred to as sensitivity in certain studies [41], [41], [50], [85], [101], [103], [104], [106], [108], [109], [116], [117], [119], recall [26], [45], [69], [72], [75], [76], [105], [105], [107], [111], [114], [121], or true positive [12], [25], [77], [82], [102], [111]–[113],…”
BackgroundMethodInfluentialPreventing Churn in Telecommunications: The Forgotten Network
Radosavljevik, D., & van der Putten, P. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41398-8_31 · Cited by 7 · cited 1×
“Several studies adopted this metric [15], [28], [32], [42], [46], [49], [50], [54], [74], [75], [77]–[81], [86], [88]–[92], [94], [95], [100], [101], [103], [106], [110], [112], [116], [119], [120], [122], [125]–[127].”
Xue, W., Sun, Y., Bandyopadhyay, S. K., & Cheng, D. (2020) · Journal of Theoretical and Applied Electronic Commerce Research · doi:10.3390/jtaer16030026 · Cited by 7 · cited 1×
“In contractual setting scenarios, such as insurance, telecommunications, and magazine subscriptions, firms can accurately understand the cash flow generated by their customers, as customers usually sign long-term contracts with firms [21].”
BackgroundA Case Study for the Churn Prediction in Turksat Internet Service Subscription
Gök, M. Ş., Özyer, T., & Jida, J. (2015) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/2808797.2808821 · Cited by 6
Vijaya, J., Sivasankar, E., & S, G. S. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1280-9_25 · Cited by 6 · cited 1×
“[50] However, certain studies did not identify the features employed [9], [12], [18], [22], [25], [42], [48], [67], [70], [73], [85], [87], [88], [97]–[99], [107], [110], [112], [113], [116], [119], [122], [127], which in some cases are related to the usage of more than one database.”
BackgroundConstruction of Bayesian Classifiers with GA for Predicting Customer Retention
Shao, H., Zheng, G., & An, F. (2008) · International Conference on Natural Computation (ICNC) · doi:10.1109/icnc.2008.724 · Cited by 5 · cited 2×
“Some studies addressed the use of genetic algorithms [26], [43], [70], [102], [122] and swarm intelligence, such as particle swarm optimization [112] and ant colony optimization [41].”
BackgroundChurn and Non-churn of Customers in Banking Sector Using Extreme Learning Machine
Mohanty, R., & Sree, C. N. R. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-10-8228-3_6 · Cited by 5 · cited 1×
“…adopted: (1) counterpropagation neural networks [85] and multilayer perceptron [28], [50], [77], [115], [121]; (2) extreme learning machines [40], [84]; (3) long short term memory [15]; (4) convolutional neural networks [15]; (5) multilayer perceptron [28], [50], [77], [115], [121]; (6)…”
Surviving Survival Analysis - An Applied Introduction
Williams, C. S. (2008) · Cited by 5
A fuzzy prediction model for calling communities
Kianmehr, K., & Alhajj, R. (2010) · International Journal of Networking and Virtual Organisations · doi:10.1504/ijnvo.2011.037162 · Cited by 3 · cited 2×
“Some studies addressed the use of genetic algorithms [26], [43], [70], [102], [122] and swarm intelligence, such as particle swarm optimization [112] and ant colony optimization [41].”
BackgroundMethodAn innovative optimized model to anticipate clients about immigration in telecom industry
Naik, M. V., & Reddy, S. S. (2017) · International Conference on Applied and Theoretical Computing and Communication Technology · doi:10.1109/icatcct.2017.8389139 · Cited by 3 · cited 1×
“…Verbeke et al. [50] However, certain studies did not identify the features employed [9], [12], [18], [22], [25], [42], [48], [67], [70], [73], [85], [87], [88], [97]–[99], [107], [110], [112], [113], [116], [119], [122], [127], which in some cases are related to the usage of more than one database.”
Backgroundbib2df: Parse a BibTeX File to a Data Frame
Ottolinger, P. (2016) · doi:10.32614/cran.package.bib2df · Cited by 3
Martono, N. P., Kanamori, K., & Ohwada, H. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13332-4_12 · Cited by 2 · cited 4×
“The f-measure is calculated with the harmonic mean of recall and precision [15], [26], [45], [69], [72], [76], [96], [105], [107], [111], [112], [114], [121].”
MethodResultInfluentialResearch on Customers Churn Prediction Model Based on Logistic
Jiang, M., Chu, N., & Bi, X. M. (2014) · Advanced materials research · doi:10.4028/www.scientific.net/amr.989-994.1517 · Cited by 2
Research works printed but not linked: 4
- Han, 2006, Data mining: Concepts and techniques
- Han, 2012, Data mining: Concepts and techniques
- 10.1016/j.ejor.2011.09.031 · DOI · Paper page
- Rätsch, A brief introduction into machine learning, 1
Cited by
Ferdinands, G., Schram, R., de Bruin, J., Bagheri, A., Oberski, D. L., Tummers, L., Teijema, J. J., & van de Schoot, R. (2023) · Systematic Reviews · doi:10.1186/s13643-023-02257-7 · Cited by 96
Predicting early user churn in a public digital weight loss intervention
Jakob, R., Lepper, N., Fleisch, E., & Kowatsch, T. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642321 · Cited by 21
“It has found application across numerous industries, notably telecommunications [50], financial services [73], gaming [36], and e-commerce [25].”
Freire, D., Mauricio, D., Castillo, J. L., & Moncayo, D. X. F. (2024) · IEEE Access · doi:10.1109/access.2024.3443318 · Cited by 12
“On the other hand, Sobreiro et al. [121] reviewed 87 articles out of 448 potentials from the period 2000-2020, identifying 60 different types of prediction algorithms; however, only 52 of these works used telecommunications datasets.”
BackgroundA Review on Machine Learning-Based Customer Churn Prediction in the Telecom Industry
Barham, S., Aweisi, N., & Khalifeh, A. F. (2023) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit58514.2023.10284430 · Cited by 7
“Different papers discussed customer s’ churn prediction from various aspects, such as the work presented in [4], which presented a systematic review in which the authors estimated the evolution of actual studies about the prediction of customers ’ dropout using ML.”
BackgroundChurn Prediction in Enterprises with High Customer Turnover
Beckhauser, W. J., & Fileto, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48316-5_19 · Cited by 3
Metadata
- Authors
- Sobreiro, P., Martinho, D. D. S., Alonso, J. G., & Berrocal, J.
- Affiliations
- Life Quality Research Centre (PT)
- ISLA Santarém - Instituto Politécnico (PT)
- Universidad de Extremadura (ES)
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 14529-14547
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4210643267
- Cited by
- 8
- References
- 132
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 3 · 2023: 3
- FWCI
- 1.40
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Department of Economy and Infrastructure of the Government of Extremadura (GR18112, IB18030)
- 4IE Project (0499-4IE-PLUS-4-E)
- European Regional Development Fund
- MCIAEIFEDERUE (RTI2018-094591-B-I00)
- Topics
- Social Sciences › Business, Management and Accounting › Marketing › Customer churn and segmentation
- Physical Sciences › Computer Science › Computer Science Applications › Online Learning and Analytics
- Social Sciences › Education › Evasion and Academic Success Factors
- Keywords
- customer churn, machine learning algorithms, feature selection, evaluation metrics, research trends, research gaps
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.