Copyright © 2025 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{187599,
        author = {Swarna Surekha and Bhuvaneswaree.p and Venkata Naga Lahari.N and Venakata SaiKumar.A and Teja Sai.V and Rithish kumar Reddy.V},
        title = {Predicting Passenger Boarding Behaviour in Public Transport Systems with Imbalanced Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {5181-5186},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187599},
        abstract = {The fast increase in the use of public transport requires proper prediction of the number of passengers getting in at each stop to facilitate proper planning of the services. Nonetheless, in practice the ridership statistics can be imbalanced between demand types, which negates the traditional machine-learning models. The paper creates a preprocessing and prediction model whereby, the temporal and operational characteristics are extracted and the demand is automatically classified into Low, Moderate, and High categories. Several models such as the Logistic Regression, Random Forest, Gradient Boosting and a Deep Neural Network (DNN) were considered. Gradient Boosting performed best with an accuracy of 0.818, overtaking the results of random forest (0.793) and Logistic Regression (0.602), but the DNN gave an accuracy of 0.719 with a better balance at the class level. This finding shows that the combination of time-based engineered functionality with strong learning algorithms can greatly increase the precision of demand prediction and offer useful information to planners in the transport sector regarding the optimization of the frequency and allocation of resources in the route.},
        keywords = {Passenger demand prediction, imbalanced data, machine learning, deep neural network, public transport analytics, temporal features, classification performance.},
        month = {November},
        }