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{176100,
        author = {MOHAMED ASFAAQ S and MUHAMMED MANZOOR M and Mr. M. Vijayakumar},
        title = {Traffic Flow Prediction using Random Forest Regressor Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {7892-7898},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176100},
        abstract = {Traffic congestion is a major issue in urban areas, affecting daily commutes, emergency services, and overall transportation efficiency. This project presents a machine learning-based traffic prediction system specifically designed for Coimbatore, leveraging historical traffic data to forecast traffic conditions at various locations. The primary objective is to provide users with an accurate estimation of traffic volume based on input parameters such as location, date, and time. By employing advanced predictive analytics, this system enhances traffic management and aids in planning optimal travel routes.
The project utilizes a Random Forest Regressor model trained on real-world traffic data collected from different areas of Coimbatore. The dataset includes essential features such as place, time, day, and historical traffic patterns. To preprocess the data, categorical variables like location and day of the week are encoded using label encoding, ensuring compatibility with the machine learning model. The model is then trained to recognize patterns and trends, enabling it to generate traffic volume predictions for given inputs.
A web-based interface has been developed using Flask and JavaScript to provide an interactive user experience. The front end allows users to input their desired location, date, and time, sending the request to the backend model for traffic prediction. The system then returns the estimated traffic condition, categorizing it into different levels such as Heavy Traffic, Normal Traffic, Low Traffic for Two-Wheelers, or Traffic Free. Additionally, a graphical representation is generated, illustrating predicted traffic volume for the next ten hours. This visualization helps users plan their journeys more effectively and make informed travel decisions.},
        keywords = {},
        month = {May},
        }