Forecasting Passenger Traffic in Metro Systems: ARIMA Analysis of Metro Ticket Reservation Data

This research study presents a comprehensive study on forecasting passenger traffic in metro systems utilizing an ARIMA (AutoRegressive Integrated Moving Average) model applied to ticket reservation data from the Pune Metro system. In increasing urbanization, metro systems face challenges such as overcrowding and fluctuating passenger demand, which adversely affect operational efficiency. The proposed ARIMA model effectively identifies temporal trends and seasonal variations in ridership, enabling accurate predictions of passenger flow patterns. Additionally, this research integrates the forecasting insights into a user-friendly application that provides real-time crowd analysis, alternative route suggestions, and peak hour traffic predictions, thereby enhancing the commuter experience. By demonstrating the practicality of machine learning techniques in public transportation planning, this study encourages the adoption of data-driven methodologies to promote more reliable and efficient metro systems. The findings underscore the potential of integrating ARIMA with other predictive models to enhance forecasting accuracy, ultimately contributing to a sustainable urban transportation ecosystem.