MENTAL STRESS PREDICTION USING MACHINE LEARNING FOR IT EMPLOYEES

Abstract

The increasing prevalence of mental stress among IT employees has become a critical concern due to demanding workloads, prolonged screen exposure, and imbalance between professional and personal life. Early identification of stress is essential to prevent long-term psychological and physiological complications. This study proposes a machine learning-based framework for detecting mental stress levels in IT professionals using a combination of behavioral, physiological, and workplace-related data. The collected data includes heart rate variability, sleep patterns, keyboard and mouse activity, screen time, and task completion metrics. After preprocessing and feature extraction, multiple machine learning algorithms such as Support Vector Machine, Random Forest, Logistic Regression, and K-Nearest Neighbors are employed for classification. Additionally, deep learning models like Long Short-Term Memory networks are utilized to capture temporal dependencies in sequential data. The performance of these models is evaluated using standard metrics including accuracy, precision, recall, and F1-score. Experimental results indicate that the proposed approach achieves high prediction accuracy, with deep learning models outperforming traditional algorithms due to their capability to learn complex patterns. The system enables real-time stress monitoring and provides actionable insights for early intervention. This research contributes to the development of intelligent workplace health monitoring systems, aiming to enhance employee well-being, reduce burnout, and improve organizational productivity. The proposed framework can be integrated into corporate environments to support proactive mental health management.