A Robust Predictive Model for Customer Churn at City Breweries Using Machine Learning Techniques
DOI:
https://doi.org/10.53819/81018102t3189Abstract
Customer churn presents a significant threat to business sustainability, particularly in the beverage industry where competition and shifting consumer preferences are intensifying. This research investigates customer churn at City Breweries, a brewery in Zimbabwe, with the aim of developing a robust predictive model using machine learning techniques. The study utilizes historical sales and operational data such as dispatch volumes, returns, mileage, and delivery routes to identify patterns associated with customer churn. Multiple classification algorithms, including Logistic Regression, Decision Trees, Random Forest, Support Vector Machines (SVM), AdaBoost, Extra Trees, and XGBoost, were implemented and compared using key performance metrics, accuracy, precision, recall, and F1-score. The results highlight XGBoost as the most effective model for churn prediction due to its ability to handle class imbalance, capture non-linear relationships, and deliver superior predictive performance. While models like Logistic Regression and Decision Trees offer simplicity and interpretability, they fall short in capturing complex interactions within the data. XGBoost’s regularization mechanisms and gradient boosting framework enhance its generalization capabilities, making it well-suited for real-world deployment. This study provides actionable insights into customer retention by identifying customers with a higher risk of churning with high accuracy. It also contributes to the existing body of knowledge by demonstrating the efficiency of ensemble machine learning models in the beverage sector, an area which is under explored in churn prediction research.
Keywords: Robust Predictive, Model, Customer Churn, City Breweries, Machine Learning Techniques
References
ABBAS, W., USMAN, M., AND QAMAR, U. (2022). Churn prediction of customers in a retail business using exploratory data analysis. In 2022 International Conference on Frontiers of Information Technology (FIT). IEEE, pp. 130–135.
ABDULLAH, D. M. AND ABDULAZEEZ, A. M. (2021). Machine learning applications based on some classification a review. Qubahan Academic Journal, 1 (2), 81–90.
AHN, J., HWANG, J., KIM, D., CHOI, H., AND KANG, S. (2020). A survey on churn analysis in various business domains. IEEE access, 8, 220816–220839.
BARRAZA, N., MORO, S., FERREYRA, M., AND DE LA PENA˜, A. (2019). Mutual information and sensitivity analysis for feature selection in customer targeting: A comparative study. Journal of Information Science, 45 (1), 53–67.
BEEHARRY, Y. AND TSOKIZEP FOKONE, R. (2022). Hybrid approach using machine learning algorithms for customers’ churn prediction in the telecommunications industry. Concurrency and Computation: Practice and Experience, 34 (4), e6627.
BOGAERT, M. AND DELAERE, L. (2023). Ensemble methods in customer churn prediction: a comparative analysis of the state-of-the-art. Mathematics, 11 (5), 1137.
BRANDUSOIU, I., TODEREAN, G., AND BELEIU, H. (2016). Methods for churn prediction in the pre-paid mobile telecommunications industry. In 2016 International conference on communications (COMM). IEEE, pp. 97–100.
BUHLMANN ¨, P. AND YU, B. (2002). Analysing bagging. The annals of Statistics, 30 (4), 927–961.
BUREZ, J. AND VAN DEN POEL, D. (2009). Handling class imbalance in customer churn prediction. Expert Systems with Applications, 36 (3), 4626–4636.
COUSSEMENT, K., BENOIT, D. F., AND VAN DEN POEL, D. (2010). Improved marketing decision making in a customer churn prediction context using generalized additive models. Expert systems with Applications, 37 (3), 2132–2143.
DAS, G. (2024). BUSINESS ENVIRONMENT. kitab writing publication.
DEVRIENDT, F., BERREVOETS, J., AND VERBEKE, W. (2021). Why you should stop predicting customer churn and start using uplift models. Information Sciences, 548, 497–515.
EHSANI, F. AND HOSSEINI, M. (2024). Customer churn prediction using a novel meta-classifier: an investigation on transaction, telecommunication and customer churn datasets. Journal of Combinatorial Optimization, 48 (1), 7.
EHSANI, F. AND HOSSEINI, M. (2025a). Consumer segmentation based on location and timing dimensions using big data from business-to-customer retailing marketplaces. Big Data, 13 (2), 111–126.
EHSANI, F. AND HOSSEINI, M. (2025b). Customer churn analysis using feature optimization methods and tree-based classifiers. Journal of Services Marketing, 39 (1), 20–35.
HADDEN, J. (2008). A customer profiling methodology for churn prediction.
HAENLEIN, M. (2013). Social interactions in customer churn decisions: The impact of relationship directionality. International Journal of Research in Marketing, 30 (3), 236–248.
HALTEH, K., ALKHOURY, R., ZIADAT, S. A., GEPP, A., AND KUMAR, K. (2024). Using machine learning techniques to assess the financial impact of the covid-19 pandemic on the global aviation industry. Transportation Research Interdisciplinary Perspectives, 24, 101043.
HANIF, I. (2020). Implementing extreme gradient boosting (xgboost) classifier to improve customer churn prediction.
IDRIS, A. AND KHAN, A. (2014). Ensemble based efficient churn prediction model for telecom. In 2014 12th International Conference on Frontiers of Information Technology. IEEE, pp. 238–244.
IMANI, M. AND ARABNIA, H. R. (2023). Hyperparameter optimization and combined data sampling techniques in machine learning for customer churn prediction: a comparative analysis. Technologies, 11 (6), 167.
IMANI, M., JOUDAKI, M., BEIKMOHAMADI, A., AND ARABNIA, H. R. (2025). Customer churn prediction: A review of recent advances, trends, and challenges in conventional machine learning and deep learning.
JONES, M. E., LOGAN, T. D., ROSE´, D., AND COOK, L. D. (2025). Competition and consumer discrimination. Technical report, National Bureau of Economic Research.
KHODABANDEHLOU, S. AND ZIVARI RAHMAN, M. (2017). Comparison of supervised machine learning techniques for customer churn prediction based on analysis of customer behaviour. Journal of Systems and Information Technology, 19 (1/2), 65–93.
KUHL, N., SCHEMMER, M., GOUTIER, M., AND SATZGER, G. (2022). Artificial intelligence and machine learning. Electronic Markets, 32 (4), 2235–2244.
LALWANI, P., MISHRA, M. K., CHADHA, J. S., AND SETHI, P. (2022). Customer churn prediction system: a machine learning approach. Computing, 104 (2), 271–294.
LARIVIERE B. AND VAN DEN POEL, D. (2004). Investigating the role of product features in preventing customer churn by using survival analysis and choice modelling: The case of financial services. Expert Systems with Applications, 27 (2), 277–285.
LEE, C. S., CHEANG, P. Y. S., AND MOSLEHPOUR, M. (2022). Predictive analytics in business analytics: decision tree. Advances in Decision Sciences, 26 (1), 1–29.
LEMMENS, A. AND GUPTA, S. (2020). Managing churn to maximise profits. Marketing Science, 39 (5), 956–973.
LE NGUYEN, K., TRINH, H. T., NGUYEN, T. T., AND NGUYEN, H. D. (2023). Comparative study on the performance of different machine learning techniques to predict the shear strength of deep beams: Model selection and industry implications. Expert Systems with Applications, 230, 120649.
LIN, W.-C. AND TSAI, C.-F. (2020). Missing value imputation: a review and analysis of the literature (2006–2017). Artificial Intelligence Review, 53, 1487–1509.
MANZOOR, A., QURESHI, M. A., KIDNEY, E., AND LONGO, L. (2024). A review on machine learning methods for customer churn prediction and recommendations for business practitioners. IEEE access.
MARTINEZ, W. L., MARTINEZ, A. R., AND SOLKA, J. (2017). Exploratory data analysis with MATLAB. Chapman and Hall/CRC.
MOZER, M. C., WOLNIEWICZ, R., GRIMES, D., JOHNSON, E., AND KAUSHANSKY, H. (1999). Churn reduction in the wireless industry. Advances in Neural Information Processing Systems, 12.
PENDHARKAR, P. C. (2009). Genetic algorithm-based neural network approaches for predicting churn in cellular wireless network services. Expert Systems with Applications, 36 (3), 6714–6720.
QI, X., YU, H., AND PLOEGER, A. (2020). Exploring influential factors including covid-19 on green food purchase intentions and the intention–behaviour gap: A qualitative study among consumers in a Chinese context. International journal of environmental research and public health, 17 (19), 7106.
SENTHILSELVI, A., KANISHK, V., VINEESH, K., AND RAJ, A. P. (2024). A novel approach to customer churn prediction in telecom. In 2024 International Conference on Advances in Computing, Communication and Applied Informatics (AC-CAI). IEEE, pp. 1–7.
VAFEIADIS, T., DIAMANTARAS, K. I., SARIGIANNIDIS, G., AND CHATZISAVVAS, K. C. (2015). A comparison of machine learning techniques for customer churn prediction. Simulation Modelling Practice and Theory, 55, 1–9.
VEISI, H. (2023). Introduction to SVM. In Learning with Fractional Orthogonal Kernel Classifiers in Support Vector Machines: Theory, Algorithms and Applications. Springer, pp. 3–18.
VERBRAKEN, T., VERBEKE, W., AND BAESENS, B. (2012). A novel profit-maximising metric for measuring classification performance of customer churn prediction models. IEEE transactions on knowledge and data engineering, 25 (5), 961–973.
WYNER, A. J., OLSON, M., BLEICH, J., AND MEASE, D. (2017). Explaining the success of adaboost and random forests as interpolating classifiers. Journal of Machine Learning Research, 18 (48), 1–33.
