The rapid proliferation of digital platform ecosystems has fundamentally altered the landscape of customer relationship management, shifting the focus from broad-based acquisition to granular, data-driven retention. However, as organizations deploy increasingly sophisticated machine learning architectures-ranging from Support Vector Machines to Deep Feedforward Neural Networks-a critical theoretical and practical paradox has emerged: the phenomenon of retention futility. This research article provides an extensive investigation into the efficacy of proactive churn prevention, synthesizing contemporary developments in propensity prediction within the financial and telecommunications industries. By analyzing the structural limitations of targeting high-risk customers, the paper argues that traditional predictive models often overlook the latent behavioral triggers that cause proactive interventions to backfire. Through a rigorous examination of the CRISP-DM framework, hyperparameter optimization via Bayesian methods, and the application of Markov chain models for session analysis, this study elucidates the complex interplay between algorithmic precision and consumer psychology. The findings suggest that while advanced "decision engines" can accurately identify customers on the verge of departure, the act of intervention itself may catalyze churn among "sleeping dogs"-customers who would have remained had they not been contacted. The article concludes with a redesigned framework for customer valuation that integrates entity embeddings and hybrid classification algorithms to move beyond simple risk assessment toward uplift modeling.

Customer Churn, Predictive Analytics, Retention Futility, Machine Learning

Ascarza, E. (2018). Retention futility: Targeting high-risk customers might be ineffective. Journal of Marketing Research, 55(1), 80–98. https://doi.org/10.1509/jmr.16.0163

Ascarza, E., Iyengar, R., & Schleicher, M. (2016). The perils of proactive churn prevention using plan recommendations: Evidence from a field experiment. Journal of Marketing Research, 53(1), 46–60. https://doi.org/10.1509/jmr.13.0483

Ascarza, E., Netzer, O., & Hardie, B. G. S. (2018). Some customers would rather leave without saying goodbye. Marketing Science, 37(1), 54–77. https://doi.org/10.1287/mksc.2017.1057

Austin, P. C. (2009). Using the standardized difference to compare the prevalence of a binary variable between two groups in observational research. Communications in Statistics - Simulation and Computation, 38(6), 1228–1234. https://doi.org/10.1080/03610910902859574

Bergstra, J., Bardenet, R., Bengio, Y., & Kégl, B. (2011). Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems (24). Curran Associates, Inc.

Bergstra, J., Yamins, D., & Cox, D. (2013). Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. Proceedings of the 30th International Conference on Machine Learning, 28, 115–123.

Blattberg, R. C., Kim, B.-D., & Neslin, S. A. (2008). Database marketing: Analyzing and managing customers. International series in quantitative marketing. Springer.

Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (2017). Classification and regression trees. Routledge. https://doi.org/10.1201/9781315139470

Burges, C. J. (1998). A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, 2(2), 121–167.

Caigny, A., Coussement, K., & Bock, K. (2018). A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees. European Journal of Operational Research, 269(2), 760–772. https://doi.org/10.1016/j.ejor.2018.02.009

Castanedo, F., Valverde, G., Zaratiegui, J., & Vazquez, A. (2014). Using deep learning to predict customer churn in a mobile telecommunication network. wiseathena.

Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T., Shearer, C., & Wirth, R. (2000). Crisp-dm 1.0 step-by-step data mining guides. NCR Syst. Eng. Copenhagen.

Chen, Z., Fu, A. W.-C., & Tong, C.-H. (2004). Optimal algorithms for finding user access sessions from very large web logs. World Wide Web, 6, 259–279.

Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.

Craven, M. (2011). Markov chain models. University of Wisconsin-Madison.

Dewey, C. (2016). Markov chain models. University of Wisconsin-Madison.

Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the thirteenth international conference on artificial intelligence and statistics, 249-256.

Guo, C., & Berkhahn, F. (2016). Entity embeddings of categorical variables. arXiv preprint arXiv:1604.06737.

Hein, A., Schreieck, M., Riasanow, T., Setzke, D. S., Wiesche, M., Böhm, M., & Krcmar, H. (2019). Digital platform ecosystems. Electronic Markets, 1-12.

Henley, W., & Hand, D. J. (1996). A k-nearest-neighbour classifier for assessing consumer credit risk. Journal of the Royal Statistical Society. Series D. The Statistician, 45, 77-95.

Hongxia, W., Xueqin, L., & Yanhui, L. (2010). Enterprise credit rating model based on fuzzy clustering and decision tree. 2010 third international symposium on information science and engineering, IEEE, 105-108.

Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression (Vol. 398). John Wiley & Sons.

Huang, Z., Chen, H., Hsu, H. J., Chen, W. H., & Wu, S. (2004). Credit rating analysis with support vector machines and neural networks: A market comparative study. Decision Support Systems, 37, 543-558.

Kayaga, S., Franceys, R., & Sansom, K. (2004). Bill payment behaviour in urban water services: Empirical data from Uganda. Journal of Water Supply: Research and Technology. AQUA, 53, 339-349.

Khashman, A. (2010). Neural networks for credit risk evaluation: Investigation of different neural models and learning schemes. Expert Systems with Applications, 37, 6233-6239.

Kim, K-j., & Ahn, H. (2012). A corporate credit rating model using multi-class support vector machines with an ordinal pairwise partitioning approach. Computers & Operations Research, 39, 1800-1811.

Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.

Krishnan, G., Bhat, A. K., & Shah, J. (2025). Decision engine: Propensity prediction in the financial industry based on customer data features. In Artificial Intelligence and Sustainable Innovation (pp. 107-112). CRC Press.