Abstract :

Portable Computing Devices Are Indispensable Tools In Academic, Professional, And Organizational Environments. Hardware Failures In These Devices Cause Significant Productivity Loss, Unplanned Downtime, And Costly Repair Procedures. Conventional Monitoring Utilities Are Reactive By Design, Generating Alerts Only After Degradation Has Already Progressed To A Visible Stage. This Paper Presents An Intelligent Predictive System That Applies Supervised Machine Learning Techniques To Analyze Key Hardware Parameters And Estimate The Probability Of Imminent Laptop Failure. A Trained Classification Model Processes Features Such As Processor Temperature, Disk Health Indicators, Memory Utilization, Fan Speed, And Battery Wear Level. Categorical Attributes Are Transformed Using Label Encoding And Numerical Features Are Normalized Through Standard Scaling To Construct A Uniform Feature Vector. The Random Forest Classifier, Trained On Historical Device Telemetry Data, Achieves A Classification Accuracy Of 94.3%, Outperforming Logistic Regression And Support Vector Machine Baselines. Predictions Are Served In Real Time Through A Flask-based RESTful API That Returns Probability Scores Together With A Four-tier Risk Categorization — Low, Medium, High, And Critical — Enabling Users To Schedule Preventive Maintenance Before Catastrophic Failure Occurs. Experimental Evaluation Demonstrates That The Proposed Framework Reduces Mean Time To Detection By 68% Compared To Threshold-based Approaches, While Maintaining An Average API Response Latency Below 120 Milliseconds. The Modular Architecture Supports Straightforward Retraining And Future Integration With Cloud-based Monitoring Platforms.

Published:

28-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

890-893

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite