Copyright © 2026 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{197523,
        author = {Harsh P. Hatade and Yash P. Ajmire and Pallavi P. Aghao and Nisarga K. Deshmukh and Sunil R. Gupta and Shailesh S. Dhok},
        title = {Scalable Demand Forecasting System for Ride-Sharing Platforms using MLOps},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {5880-5889},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197523},
        abstract = {Ride-sharing platforms face complex operational challenges owing to their dynamic and region-specific nature of demand. This varies considerably depending on peak hours, weather conditions, traffic jams, and other public events, which lead to inefficient utilization of drivers, long waiting times for passengers, and uneven earnings for drivers. Using MLOps, the present study aims to create a Scalable Demand Forecasting System for Ride-Sharing Platforms, which will be able to produce precise short-term demand forecasts for different urban areas. In the suggested system, a hybrid strategy will be used, with Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) models being used to forecast demand trends. The results of both models will be combined using an ensemble method to produce more accurate and reliable outcomes. Furthermore, this system will include a comprehensive MLOps workflow for the seamless and automated deployment, integration, and monitoring of the application. The application will be containerized using Docker and hosted on the Render cloud platform for a more efficient and consistent hosting experience. The proposed solution is designed to enhance operational efficiency, minimize downtime for drivers, and improve the passenger experience, as well as offer a forecasting solution for the ridesharing industry.},
        keywords = {Demand Forecasting, Ride-Sharing Platforms, Time-Series Prediction, LSTM, XGBoost, Ensemble Learning, MLOps, Cloud Deployment, Docker Containerization, CI/CD Automation},
        month = {April},
        }