This paper presents SmartRail, a machine learning-based train delay prediction and passenger advisory system developed as a final year project. The system uses a Random Forest regression model trained on a structured dataset to estimate train delays based on journey attributes such as category, season, day, and distance. The system provides additional features including delay reason analysis, passenger advisory, and station wait planning through a web-based interface built using Flask, HTML, CSS, JavaScript, and SQLite. The model achieved an R² score of 0.9014 and a mean absolute error of 7.98 minutes on the test dataset. Although the current implementation uses synthetic data, it demonstrates the potential of predictive analytics in improving railway passenger decision-making and intelligent transport systems.
Singh et al. (Sun,) studied this question.