Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174595,
        author = {Mr.R.Umapathi and Mrs.G.V.Kanimozhi and Dr.K.Sasikala and Mrs.G.Gayathri and Mrs.G.Kanmani and Mrs.A.Shanthi},
        title = {Machine Learning Driven Predictive Analytics for Customer Churn in Bus Transportation System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {104-108},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174595},
        abstract = {Public transportation is essential for urban mobility, yet ridership continues to decline due to various service-related and socio-economic factors. This study develops a machine learning-driven predictive analytics model to identify passengers at risk of discontinuing public transport usage. By leveraging historical travel data, fare utilization trends, and external variables, the model employs ensemble learning techniques, specifically Random Forest and Deep Forest, to enhance predictive accuracy. The system integrates a structured database architecture for real-time churn prediction and decision-making support. Performance evaluation is conducted using key churn prediction metrics such as precision, recall, F1-score, AUC-ROC, and log-loss to ensure model reliability. Experimental results demonstrate that the Deep Forest algorithm achieves an AUC-ROC score of 0.92 and an F1-score of 0.89, significantly outperforming traditional models. The real-time decision support system provides actionable insights, allowing transport authorities to dynamically optimize routes and service strategies for improved commuter experience. The study highlights the potential of AI-driven predictive analytics in enhancing passenger retention and ensuring sustainable urban mobility. Additionally, the analysis reveals that real-time fare adjustments based on passenger behavior further optimize transport efficiency. Finally, the system's adaptability to varying urban transport infrastructures ensures its applicability across different transit networks.},
        keywords = {Commuter Retention, Data Science, Deep Forest, Machine Learning, Passenger Churn Prediction, Predictive Analytics, Public Transport, Smart Mobility, Urban Transit.},
        month = {March},
        }