Virtual Booth

Accurate forecasting of public transport ridership helps improve scheduling, planning, and resource management. A time series model was used to analyze daily ridership patterns over a specific period. The selected model showed good performance, with a mean absolute percentage error of 9.17 percent, indicating strong predictive ability. The results suggest that traditional forecasting models can provide useful insights for short-term planning. However, their accuracy may be affected by unexpected events. Future research should consider including external factors such as weather and economic conditions or exploring modern approaches like machine learning to enhance forecasting accuracy and flexibility.