Riding into the Future: Transforming Jordan’s Public Transportation with Predictive Analytics and Real-Time Data

Abstract

Introduction: this study explores how predictive analytics and real-time data integration can improve efficiency in Jordan’s public transportation network. By addressing scheduling, route optimization, and congestion management, it responds to growing urban transit demands in the region. Method: data were collected over three months from official ridership logs, GPS-enabled buses, and traffic APIs. ARIMA-based time-series forecasting captured historical trends, while a Random Forest model incorporated congestion index, average wait times, and other operational variables. Metadata management protocols (JSON/XML) facilitated cross-agency data sharing. Results: ARIMA proved effective for short-term passenger demand projections, although it occasionally underpredicted sudden ridership peaks. The Random Forest approach yielded stronger overall accuracy, explaining roughly 85 % of variation when combining real-time congestion data with historical records. Real-time streams further supported dynamic scheduling and route adjustments. Conclusion: combining predictive models with IoT-based data integration can enhance reliability and user satisfaction in Jordan’s public transit system. Although limited by timeframe and route scope, the findings underscore the importance of multi-agency collaboration and ongoing policy support to sustain data-driven innovations.