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{204589,
        author = {Aman Baheti and Dr R Savitha},
        title = {AI-Based Smart Resource Manager for System Optimisation Using Machine Learning and Web Technologies},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2801-2804},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204589},
        abstract = {Modern laptops and personal computers run dozens of applications at the same time, and users often have no idea why things start slowing down or when it is going to get worse. Standard tools like Windows Task Manager or Linux top only show a snapshot of what is happening right now — they do not predict what is coming or tell you what to do about it. This paper describes a system we built called the AI-Based Smart Resource Manager which monitors CPU, RAM, Disk, and Battery usage in real time, uses a Random Forest machine learning model to predict resource usage five seconds ahead, and generates smart suggestions through a four-engine recommendation system. We also built a web version using Flask so that any user can open a browser, register, and start seeing their own personalised dashboard without downloading any project code. A role-based access system keeps each user's data private while letting an admin see aggregated health scores across all connected machines. We tested the system with multiple users and found that the Random Forest model achieved a Mean Absolute Error of 4.3% and an R² score of 0.87. The web app was deployed on Render.com and worked correctly across three simultaneous users during our tests.},
        keywords = {anomaly detection, Flask, machine learning, predictive analytics, psutil, Random Forest, role-based access, system resource monitoring, web dashboard},
        month = {June},
        }