Customer Churn Prediction Using Hybrid Machine Learning Models: Implications for Customer Retention Strategy

Main Article Content

Anu Sharma

Abstract

Churn prediction is one of the most mature applications of machine learning in marketing, yet two gaps persist: the incremental value of hybrid (ensemble-of-ensembles) models over their components is rarely quantified in economic terms, and the link between a model’s ranking quality and the design of the retention campaign that consumes its scores is often left implicit. This paper addresses both gaps using a simulation harness that generates 8,000 subscription customers from a logistic process with a known interaction between price increases and contract status. A stacked hybrid that combines logistic regression, random forest and gradient boosting through a logistic meta-learner is compared with its three components on discrimination, calibration, top-decile lift and the net value of a retention campaign under four contact budgets. The hybrid achieves the highest top-decile lift (4.50) and the highest campaign net value at every budget, although its AUC (0.803) is marginally below that of logistic regression (0.807), illustrating that global discrimination and campaign value can diverge. Net value peaks when the top 10% of customers are contacted and declines at wider budgets. The paper derives a budget-setting rule from the gains curve and discusses how calibrated churn probabilities, responsiveness estimates and customer value should be combined in retention strategy.

Article Details

Section

Articles

How to Cite

Sharma, A. (2026). Customer Churn Prediction Using Hybrid Machine Learning Models: Implications for Customer Retention Strategy. International Journal of Humanities and Information Technology, 8(4), 25-30. https://doi.org/10.21590/ijhit.08.04.04

References

Ahuja, R. (2026). Adoption of secure session management in multi-device applications for mitigating session hijacking and replay attacks through token rotation and expiry controls. Journal of Integrative Science and Societal Impact, 2(1), 101–108. https://doi.org/10.29121/JISSI.v2.i1.2026.49

Anchala, S. (2019). Database security challenges in cross-border data flows: Analysing compliance, privacy, and risk in international data transfers. International Journal of Advanced Research in Education and Technology, 6(3), 831–838. https://doi.org/10.15680/IJARETY.2019.0603016

Dwivedi, D. (2026). Agentic AI and the future of artificial general intelligence: A study on how goal-oriented autonomous agents contribute to the development of more human-like intelligence, reasoning, and decision-making abilities. Journal of Integrative Science and Societal Impact, 2(1), 72–79. https://doi.org/10.29121/JISSI.v2.i1.2026.44

Rangappa, A. S. (2026). The architecture of agentic AI systems: A technical study on planning, memory, goal-oriented reasoning, and environment interaction for building robust autonomous agents. Journal of Integrative Science and Societal Impact, 2(1), 39–46. https://doi.org/10.29121/9shxnt36

Khan, S. (2023). AI-powered innovations in cross-border merchant payment systems: Exploring the role of artificial intelligence in enhancing speed, transparency, and trust in international financial transactions. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 12(5), 1217–1224. https://doi.org/10.15662/IJAREEIE.2023.1205026

Aggarwal, A. (2018). Implementation of cloud security automation in continuous integration pipelines for accelerating DevSecOps adoption and minimizing manual misconfigurations through security-as-code. International Journal of Innovative Research in Science, Engineering and Technology, 7(11). https://doi.org/10.15680/IJIRSET.2018.0711083

Dwivedi, D. (2024). Agentic AI and global governance: Addressing the challenges of regulating autonomous artificial agents across borders in a digitally interconnected world. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 13(11), 2527–2534. https://doi.org/10.15662/IJAREEIE.2024.1311011

Mahajan, R. A., Dey, R., Khan, M., Kanabar, K., & Gupta, S. K. (2025). Real-time vehicular-to-vehicular (V2V) communication and applications for pedestrian safety in AI-optimized VANETs for autonomous vehicles. In H. Maryam, M. M. Malik, I. U. Khan, & S. K. Gupta (Eds.), AI-driven transportation systems: Real-time applications and related technologies (pp. 151–167). Springer. https://doi.org/10.1007/978-3-031-98349-8_8

Bhaskara Raju Rallabandi. (2023). NATIVE OBSERVABILITY FOR PRIVATE 5G: A REFERENCE ARCHITECTURE ON COMBINATION OF NWDAF, SMO, AND EDGE ANALYTICS. American Journal of AI Cyber Computing Management, 3(1), 24–28. https://doi.org/10.64751/ajaccm.2023.v3.n1.pp24-28

Anchala, S. (2018). Adoption of infrastructure as code security validation in cloud-native environments for reducing configuration drifts and compliance violations through automated template scanning. International Journal of Innovative Research in Science, Engineering and Technology, 7(10), 8305–8313. https://doi.org/10.15680/IJIRSET.2018.0710087

Gupta, A. (2025). Agentic AI for national security and defense: An analytical study on autonomous agents in surveillance, strategic decision-making, and military operations with a focus on ethical and legal boundaries. Journal of Digital Security and Forensics, 2(1), 163–175. https://doi.org/10.29121/digisecforensics.v2.i1.2025.84

Chatrath, A. (2018). The impact of containerization on DevSecOps: Security considerations for Docker, Kubernetes, and microservices architectures in continuous deployment pipelines. International Journal of Advanced Research in Education and Technology, 5(6). https://doi.org/10.15680/IJARETY.2018.0506019

Ahuja, R. (2024). Deployment of content security policies in front-end frameworks for blocking cross-site scripting and clickjacking through declarative access restrictions. International Journal of Multidisciplinary Research in Science, Engineering and Technology, 7(11), 17234–17242. https://doi.org/10.15680/IJMRSET.2024.0711132

Chatrath, A. (2019). A multi-layered DevSecOps framework: Integrating secure coding, automated testing, vulnerability scanning, and incident response into end-to-end software development lifecycles. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 8(3). https://doi.org/10.15662/IJAREEIE.2019.0803102

Mahajan, R., Kanabar, K., Dey, R., Jadhav, P. V., Khan, M., & Karimullah, S. (2026). Blockchain complementary model: A new way of devouring smart data by driverless vehicles for next-generation communication. In S. K. Singh, R. B. Jadeja, A. Khanna, P. K. Dutta, & B. Virdee (Eds.), Security paradigms in 6G smart cities and IoT ecosystems: Navigating the future (pp. 115–126). CRC Press. https://doi.org/10.1201/9781003564645-8

Gupta, A. (2025). Blockchain-enhanced cloud security: Exploring decentralized trust models, data integrity verification, and secure cloud auditing mechanisms. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 14(1). https://doi.org/10.15662/IJAREEIE.2025.1401019

Aggarwal, A. (2018). Implementation of quantum cryptography in financial transactions for enhancing data confidentiality and resisting future quantum attacks through secure key distribution mechanisms. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 7(7), 3196–3204. https://doi.org/10.15662/IJAREEIE.2018.0707016

Khan, S. (2023). AI-driven speech and voice analytics in CRM platforms: A study on intelligent call center automation, emotion recognition, and service personalization. International Journal of Multidisciplinary Research in Science, Engineering and Technology, 6(2), 510–517. https://doi.org/10.15680/IJMRSET.2023.0602035

Kumar, S., Sharma, K., Kumar, P. A., Jain, A., Bhagat, S. K., & Singh, P. (2024, September). An improved particle swarm approach for energy-aware location-aided routing in mobile ad-hoc network. In 2024 7th International Conference on Contemporary Computing and Informatics (IC3I) (Vol. 7, pp. 1119–1124). IEEE.

Mahadasu, S. S. (2020). Cloud-native life cycle management of virtualized RAN functions using Kubernetes operators and policy-driven automation. International Journal of Engineering Science and Advanced Technology, 20(4), 21–26. https://doi.org/10.64771/ijesat.2020.v20.i04.pp3846

Bhaskara Raju Rallabandi. (2022). SUB-MICROSECOND 5G SYNC FOR RELIABLE FACTORY ROBOT CONTROL. American Journal of Management and IOT Medical Computing, 1(1), 34–39. https://doi.org/10.64751/ajmimc.2022.v1.n1.pp34-39

Aggarwal, A. (2018). Application of federated learning in medical IoT devices for preserving patient privacy and preventing data breaches through decentralized cyber defense models. International Journal of Innovative Research in Computer and Communication Engineering, 6(3), 2654–2660. https://doi.org/10.15680/IJIRCCE.2018.0603167

Mahadasu, S. S. (2021). Telemetry-assisted mobility management for 5G standalone networks with distributed edge user-plane functions. International Journal of Engineering Research and Science & Technology, 17(1), 141–145. https://doi.org/10.62643/ijerst.2019.v17.n1.4406

Dwivedi, D. (2025). A comparative study of public, private, and hybrid cloud security architectures: Evaluating trade-offs in scalability, privacy, cost, and risk management. International Journal of Multidisciplinary Research in Science, Engineering and Technology, 8(1), 485–493. https://doi.org/10.15680/IJMRSET.2025.0801069

Bhaskara Raju Rallabandi. (2024). DIGITAL TWIN–DRIVEN 6G CAMPUS NETWORKS: INTELLIGENT FAULT RECOVERY AND ENERGY OPTIMIZATION. American Journal of AI Cyber Computing Management, 4(3), 30–34. https://doi.org/10.64751/ajaccm.2024.v4.n3.pp30-34

Devulapalli, N. (2024). Agentic AI in finance and economics: The role of autonomous agents in fraud detection, algorithmic trading, credit risk assessment, and ethical governance of automated financial systems. International Journal of Multidisciplinary and Scientific Emerging Research, 12(4), 1958–1964. https://doi.org/10.15662/IJMSERH.2024.1204057

Bhaskara Raju Rallabandi. (2022). DETERMINISTIC STABILITY ANALYSIS FOR PRODUCTION-LINE CONTROL OVER PRIVATE 5G. American Journal of AI Cyber Computing Management, 2(4), 33–37. https://doi.org/10.64751/ajaccm.2022.v2.n4.pp33-37

Kumar, S., Ghai, D., Jain, A., Tripathi, S. L., & Rani, S. (Eds.). (2023). Multimodal biometric and machine learning technologies: Applications for computer vision. John Wiley & Sons.

Ahuja, R. (2025). The risks and opportunities of generative AI in cyber security: Investigating the dual-use nature of generative models for phishing, malware development, and defence through synthetic data and automated threat detection. International Journal of Innovative Research in Computer and Communication Engineering, 13(2), 1758–1767. https://doi.org/10.15680/IJIRCCE.2025.1302059

Mahadasu, S. S. (2019). Performance-aware VNF placement for distributed 5G core networks over heterogeneous edge and cloud infrastructure. International Journal of Engineering Science and Advanced Technology, 19(10), 5–11. https://doi.org/10.64771/ijesat.2019.v19.i10.pp3849

Agrawal, N. K., Kumar, S., Bisht, G. S., Srivastav, A., Bansla, V., & Jain, A. (2024, May). Development of a novel quality of service aware video streaming on demand system for the Internet of Thing enabled MANET. In 2024 International Conference on Communication, Computer Sciences and Engineering (IC3SE) (pp. 80–85). IEEE.

Devulapalli, N. (2026). A comparative study of predictive AI and agentic AI: Examining key differences in autonomy, goal orientation, human interaction, and system accountability. Journal of Integrative Science and Societal Impact, 2(1), 80–87. https://doi.org/10.29121/JISSI.v2.i1.2026.45

Rangappa, A. S. (2025). Agentic AI and cyber security: Autonomous threat hunting, intrusion detection, and adaptive defense mechanisms in a world of increasingly sophisticated cyber attacks. Journal of Digital Security and Forensics, 2(1), 128–138. https://doi.org/10.29121/digisecforensics.v2.i1.2025.86

Bhanushali, B. (2018). Risk-based approaches in anti-money laundering for balancing regulatory compliance costs and maximizing detection of high-risk financial activities. International Journal of Innovative Research in Computer and Communication Engineering, 6(11), 9006–9014. https://doi.org/10.15680/IJIRCCE.2018.0611081

Jaiswal, I. A., & Khan, S. (2025). Leveraging cloud-based projects (AWS) for microservices architecture. Universal Research Reports, 12(1), 195–202.

Bhanushali, B. (2019). Graph-based network analysis for identifying complex money laundering typologies, detecting suspicious transaction chains, and tracing illicit financial flows. International Journal of Multidisciplinary and Scientific Emerging Research, 7(4), 2007–2014. https://doi.org/10.15662/IJMSERH.2019.0704047

Anchala, S. (2018). Deployment of container image scanning in DevSecOps pipelines for mitigating open-source vulnerabilities and ensuring runtime safety through CVE-based detection mechanisms. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 7(3), 1546–1554. https://doi.org/10.15662/IJAREEIE.2018.0703058

Talasila, D. (2024). Implementation of secure DevOps pipelines in cloud-native applications for ensuring code integrity and reducing vulnerability exposure through automated security integration. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 13(11), 2535–2543. https://doi.org/10.15662/IJAREEIE.2024.1311012

Rangappa, A. S. (2024). Application of AI-augmented log analysis in Dev Sec Ops monitoring for accelerating incident response and root cause analysis through pattern recognition and auto-correlation. International Journal of Multidisciplinary Research in Science, Engineering and Technology, 7(10), 16135–16142. https://doi.org/10.15680/IJMRSET.2024.0710081

Khan, S. (2025). The role of artificial intelligence in cyber security: Leveraging machine learning and predictive analytics for intrusion detection, threat intelligence, and autonomous defense mechanisms. The Research Journal, 11(3), 1–7.

Chatrath, A. (2019). DevSecOps in Agile and Lean development: Examining the alignment of security, speed, and scalability in rapid iteration and continuous delivery environments. International Journal of Multidisciplinary and Scientific Emerging Research, 7(3), 1506–1513. https://doi.org/10.15662/IJMSERH.2019.0703046

Gupta, A. (2026). Bias, fairness, and inclusivity in generative AI systems: A critical examination of algorithmic bias, representation gaps, and the challenges of ensuring equity in AI-generated outputs. Journal of Integrative Science and Societal Impact, 2(1), 23–30. https://doi.org/10.29121/JISSI.v2.i1.2026.38

Bhanushali, B. (2019). Integration of biometric authentication with AML systems for strengthening know-your-customer (KYC) processes and reducing identity fraud in financial institutions. International Journal of Advanced Research in Education and Technology, 6(5), 853–860. https://doi.org/10.15680/IJARETY.2019.0605019

Talasila, D. (2026). Agentic AI in multi-agent systems: Exploring the coordination, negotiation, and cooperation of autonomous artificial agents in competitive and collaborative digital ecosystems. Journal of Integrative Science and Societal Impact, 2(1), 64–71. https://doi.org/10.29121/JISSI.v2.i1.2026.43

Devulapalli, N. (2025). Machine learning in database security: Leveraging anomaly detection, intrusion detection, and predictive analytics for proactive threat prevention. International Journal of Innovative Research in Science, Engineering and Technology, 14(2), 1685–1692. https://doi.org/10.15680/IJIRSET.2025.1402105

Burnout in Global Healthcare Systems: Psychosocial Determinants, Regional Realities, and Behavioral Optimization Pathways. [Author/source details missing in supplied list]

Jain, J., Jain, A., Srivastava, S. K., Verma, C., Raboaca, M. S., & Illés, Z. (2022). Improved security of e-healthcare images using hybridized robust zero-watermarking and hyper-chaotic system along with RSA. Mathematics, 10(7), 1071.

Kanabar, K., Dey, R., Mahajan, R., Jadhav, P. V., Khan, M., & Ghantasala, G. S. P. (2026). The benefits of web and blockchain in decision-making for Industry 4.0. In S. K. Singh, R. B. Jadeja, A. Khanna, P. K. Dutta, & B. Virdee (Eds.), Security paradigms in 6G smart cities and IoT ecosystems: Navigating the future (pp. 289–304). CRC Press. https://doi.org/10.1201/9781003564645-18

Jain, A. (2024, December). Energy-efficient signal processing architectures for IoT networks design. In 2024 International Conference on Emerging Technologies and Innovation for Sustainability (EmergIN) (pp. 362–367). IEEE.

Mahadasu, S. S. (2022). GitOps-based continuous delivery of cloud-native 5G network functions with automated configuration validation. International Journal of Data Science and IoT Management System, 1(1), 50–56. https://doi.org/10.64751/ijdim.2022.v1.n1.1286

Talasila, D. (2025). Adoption of dynamic application security testing (DAST) in DevOps lifecycles for identifying runtime vulnerabilities and business logic flaws through continuous fuzzing and penetration testing. International Journal of Multidisciplinary Research in Science, Engineering and Technology, 8(2), 1192–1200. https://doi.org/10.15680/IJMRSET.2025.0802092

Similar Articles

You may also start an advanced similarity search for this article.