productivity, job satisfaction, and the success of organizations. Many companies struggle to monitor mental health and engagement effectively. Traditional methods like manual surveys and HR interviews often miss the mark on accuracy, efficiency, and scalability. To tackle this problem, this project introduces a web-based Employee Well-Being Prediction System. It combines structured psychometric surveys with machine learning to deliver automated, data-driven insights into workplace well-being. The system uses the Python Flask framework and an SQLite database for secure user management. It also stores employee responses in Excel. Features include secure login and registration for employees and administrators, structured survey modules, automated score calculation, and predictive modeling of employee well-being. Survey responses are gathered across six areas: recognition, workplace environment, team support, career growth, work-life balance, and emotional state. At the heart of the system is the Decision Tree algorithm, chosen for its simplicity and effectiveness in classification tasks. The model analyzes section scores and creates clear decision rules to classify employees' well-being status, ensuring transparency and accuracy in predictions. In addition to making predictions, the system improves usability through visual outputs like pie charts to show score distributions. An integrated admin dashboard lets HR professionals monitor employee responses, track well-being trends, and spot potential risks such as disengagement or burnout. By merging psychometric assessment with Decision Tree modeling, the project offers organizations a practical tool to improve workplace conditions, enhance employee support, and make informed HR choices. This method shows how web technologies and machine learning can work together to create smart solutions for employee engagement, offering immediate insights and laying the groundwork for future improvements like interactive dashboards and advanced AI models.