Journal of Quality Engineering and Production Optimization

Journal of Quality Engineering and Production Optimization

A Hybrid Model for Customer Churn Prediction: An Optimized Combination of Multilayer Perceptron and Atomic Orbital Search

Document Type : 20th IIIE Conference Selected Papers

Authors
Leila Zolqadr 1
Majid Shakhsi-Niaei 1
Azam Safari 2
1 Department of Industrial Engineering, Yazd University, Yazd, Iran
2 Department of Information Technology, Holy Shrine Fatemeh Masoumeh (SA), Qom, Iran
10.22070/jqepo.2025.20710.1304
Abstract
Customer churn is a formidable and persistent challenge for the telecommunications sector, as it significantly erodes profitability and impedes sustainable competitive advantage. Conventional machine learning methods often exhibit limitations in capturing non-linear intricacies and effectively managing voluminous, high-dimensional datasets. To address these issues, this study presents a novel hybrid predictive framework for enhanced customer churn prediction. Our proposed methodology integrates an optimized Multilayer Perceptron (MLP) with the Atomic Orbital Search (AOS) metaheuristic algorithm. Crucially, AOS is systematically deployed to fine-tune the critical connection weights and biases of the MLP architecture, mitigating issues such as premature convergence and suboptimal parameter selection that are common in standalone neural networks. Empirical validation, conducted using the comprehensive Teldata dataset (7043 instances, 20 features) in MATLAB, unequivocally demonstrates the hybrid approach's superior efficacy over established conventional methodologies. Specifically, the hybrid MLP-AOS model achieved an impressive predictive accuracy of 97.8% on the test subset, a notable improvement over the 79% achieved by Support Vector Machines (SVMs) and the 75% achieved by a conventional MLP. These compelling findings underscore the proposed approach's ability to predict customer churn with heightened precision, providing telecommunications management with an analytical tool for identifying pivotal influencing factors and formulating effective retention strategies.
Keywords
Customer Churn Prediction, Multilayer Perceptron (MLP), Atomic Orbital Search (AOS), Evolutionary Optimization, Hybrid Model, ">Support Vector Machines (SVMs).
Abbaspour Ghadim Bonab, A., & Yousefi Nejad Attari, M. (2022). A predictive data-driven state-dependent decision approach to determine inventory system states for critical spare parts. Journal of Quality Engineering and Production Optimization, 1(2), pp.1–13.
Adwan, O., Faris, H., Jaradat, K., Harfoushi, O., & Ghatasheh, N. (2014). Predicting customer churn in the telecom industry using multilayer perceptron neural networks: Modeling and analysis. Journal of Computer Science and Technology, 11(3), pp.75–81.
Alsiehemy, A. (2019). An Assessment of Customer Retention with Self-Service Technologies: A Model Development. Business Management and Strategy, 10(1), pp.78–92.
Amin, A., Anwar, S., Adnan, A., Nawaz, M., Alawfi, K., Hussain, A., & Huang, K. (2017). Customer churn prediction in the telecommunications sector using a rough set approach. Neurocomputing, 237, pp.242–254.
Azizi, M. (2020). Atomic orbital search: A novel metaheuristic algorithm. Applied Mathematical Modelling, 89(1), pp.123–134.
Azizi, M., Talatahari, S., Khodadadi, N., & Sareh, P. (2022). Multiobjective Atomic Orbital Search (MOAOS) for Global and Engineering Design Optimization. IEEE Access, 10, pp. 67727–67746.
Behdinian, A., Amani, M. A., Aghsami, A., & Jolai, F. (2022). An Integrating Machine Learning Algorithm and Simulation Method for Improving Software Project Management: A Case Study. Journal of Quality Engineering and Production Optimization, 1(2), pp.1–11.
Bhushan, S. B. (2024). Enhancing Customer Churn Prediction in the Telecom Sector Using Advanced Machine Learning Techniques and Explainable AI [Master's Research Project, National College of Ireland]. National College of Ireland Institutional Repository (NORMA). https://norma.ncirl.ie/8683/
Bi, W., Cai, M., Liu, M., & Li, G. (2016). A big data clustering algorithm for mitigating the risk of customer churn. IEEE Transactions on Industrial Informatics, 12(3), pp.1270–1281.
Boobier, T. (2018). Advanced analytics and AI: Impact, implementation, and the future of work. Hoboken, NJ: John Wiley & Sons.
Chai, E., Khadullo, K., & Tole, K. (2025). Enhancing customer churn prediction: Addressing disparities and imbalances in machine learning models. Journal of Machine Learning Research, 13(3), pp.129–148.
Chugh, A., Sharma, V. K., Bhatia, M. K., & Jain, C. (2022). A big data query optimization framework for telecom customer churn analysis. In A. Khanna, S. Bhattacharyya, S. Anand, D. Gupta, A. E. Hassanien, & A. Jaiswal (Eds.), Advances in Intelligent Systems and Computing (pp. 475–484). Singapore: Springer.
Deng, W., Deng, L., Liu, J., & Qi, J. (2019). Sampling method based on an improved C4.5 decision tree and its application in the prediction of telecom customer churn. International Journal of Information Technology and Management, 18(1), pp.93–109.
Ever, Y. K., Dimililer, K., & Sekeroglu, B. (2019). Comparison of machine learning techniques for prediction problems. In L. Barolli, M. Takizawa, F. Xhafa, & T. Enokido (Eds.), Web, Artificial Intelligence and Network Applications: Proceedings of the Workshops of the 33rd International Conference on Advanced Information Networking and Applications (WAINA-2019) (pp. 713–723). Matsue, Japan: Springer.
Géron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). Sebastopol, CA: O'Reilly Media.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. Cambridge, MA: MIT Press.
Han, H., Back, K.-J., & Barrett, B. (2009). Influencing factors on restaurant customers’ revisit intention: The roles of emotions and switching barriers. International Journal of Hospitality Management, 28(4), pp.563–572.
Huettmann, F., Craig, E. H., Herrick, K. A., Baltensperger, A. P., Humphries, G. R. et al. (2018). Use of machine learning (ML) for predicting and analyzing ecological and ‘presence only’ data: An overview of applications and a good outlook. In F. Huettmann, D. J. Lieske, S. N. R. Mohseni, E. H. Craig, & S. C. L. Li (Eds.), Machine Learning for Ecology and Sustainable Natural Resource Management (pp. 27–61). Cham: Springer.
Hossein Khani, N., Hosseini Motlagh, S. M., & Khakzar Bafruei, M. (2014). Identification of factors affecting customer churn in the insurance industry. Paper presented at the 21st National and 7th International Insurance and Development Conference, Tehran, Iran. SID. https://sid.ir/paper/833543/fa
Lalwani, P., Mishra, M. K., Chadha, J. S., & Sethi, P. (2021). Customer churn prediction system: a machine learning approach. Computing, 104, pp.271–294.
Lee, J., Lee, J., & Feick, L. (2001). The impact of switching costs on the customer satisfaction‐loyalty link: Mobile phone service in France. Journal of Service Management, 15(1), pp.35–48.
Manzoor, A., Qureshi, M. A., Kidney, E., & Longo, L. (2024). A Review on Machine Learning Methods for Customer Churn Prediction and Recommendations for Business Practitioners. IEEE Access, 12, pp.70434–70445.
Maskale, V., Vaidya, V., Patil, Y., Bagal, Y., & Dhamdhre, V. (2024, April). To Design and implement an Application for Bank Customer Churning Rate Prediction and Analysis using a Machine Learning Algorithm. In 2024, MIT Art, Design and Technology School of Computing International Conference (MITADTSoCiCon) (pp. 475–484). Pune, India: IEEE.
Movafaghpour, M. A. (2023). Predicting Project Delays Using a New Trended Regression Tree Method. Journal of Quality Engineering and Production Optimization, 2(1), pp.29–41.
Neslin, S. A., Gupta, S., Kamakura, W., Lu, J., & Mason, C. H. (2006). Defection detection: Measuring and understanding the predictive accuracy of customer churn models. Journal of Marketing Research, 43(2), pp.204–211.
Nielsen, M. A. (2015). Neural Networks and Deep Learning. Determination Press.
Noe, R. A., Hollenbeck, J. R., Gerhart, B., & Wright, P. M. (2017). Human resource management: Gaining a competitive advantage. New York, NY: McGraw-Hill Education.
Pustokhina, I. V., Pustokhin, D. A., Aswathy, R., Jayasankar, T., Jeyalakshmi, C., & Díaz, V. G. (2021). Dynamic customer churn prediction strategy for business intelligence using text analytics with evolutionary optimization algorithms. Computers & Industrial Engineering, 162, 107606.
Rai, S., Khandelwal, N., & Boghey, R. (2020). Analysis of customer churn prediction in the telecom sector using the CART algorithm. In A. K. Luhach, J. A. Kosa, R. C. Poonia, X.-Z. Gao, & D. Singh (Eds.), Sustainable Technologies for Computational Intelligence: Proceedings of ICSTCI 2020 (AISC, Vol. 1045, pp. 457–466). Ghaziabad, India: Springer.
Ramesh, P., Jeba Emilyn, J. & Vijayakumar, V. (2022). Hybrid Artificial Neural Networks Using Customer Churn Prediction. Wireless Personal Communications, 124, pp.1695–1709.
Rani, K. S., Thaslima, S., Prasanna, N. G., Vindhya, R., & Srilakshmi, P. (2021). Analysis of Customer Churn Prediction in Telecom Industry Using Logistic Regression. International Journal of Innovative Research in Computer Science & Technology, 9(4), pp.2347–5552.
Ren, C. R., Hu, Y., & Cui, T. (2019). Responses to rival exit: Product variety, market expansion, and preexisting market structure. Strategic Management Journal, 40(2), pp.253–276.
Sagming, M., Heymann, R., & Visaya, M. V. (2025). Using topological data analysis and machine learning to predict customer churn. Journal of Big Data, 12(4), pp.320–338.
Sato, T., Huang, B. Q., Huang, Y., Kechadi, M.-T., & Buckley, B. (2010). Using PCA to predict customer churn in a telecommunication dataset. In L. Cao, Y. Liu, C. Zhang, & H. Zhu (Eds.), Advanced Data Mining and Applications: 6th International Conference, ADMA 2010 (Lecture Notes in Computer Science, Vol. 6460, pp. 198–208). Chongqing, China: Springer.
Zhang, T., Moro, S., & Ramos, R. F. (2025). A data-driven approach to improve customer churn prediction based on telecom customer segmentation. Journal of Machine Learning Research, 13(5), pp.213–229.
Journal of Quality Engineering and Production Optimization
Volume 10, Issue 1
May 2025
Pages 71-90