Vibration can have both short-term and long-term effects on the human body, depending on factors such as the frequency, amplitude, duration, and type of vibration, as well as individual susceptibility and exposure levels. It's necessary to understand that each person will experience the impacts of vibration exposure differently ranging from simple nausea and discomfort to chronic HAVS (Human Arm Vibration Syndrome) and Raynaud’s Syndrome. HAVS is an occupational health condition resulting from prolonged and repetitive exposure to Human Arm Vibration (HAV) within industrial settings experiencing vibration levels from 6.3 Hz to 1250 Hz. Due to rapid industrialization early detection and risk assessment of HAVS have become crucial to mitigate its adverse effects on the well-being of workers. Early detection and risk assessment of HAVS have become crucial to mitigate its adverse effects on the well-being of workers. This paper focus on prediction of HAVS in Foundry workers who are exposed to HAV for long durations with help of Machine Learning technique called Linear Support-Vector Machine Algorithm (LSVM). The LSVM model offers a practical and interpretable framework for risk assessment. The SVM's linear nature allows for transparent decision boundaries, enhancing the understanding of key predictors and their impact on HAVS susceptibility. By proving the efficiency of Linear SVMs in early HAVS identification, this paper advances the idea of predictive modelling for occupational health and safety. It also highlights the potential for machine learning methods to enhance workers’ wellbeing and encourages the creation of proactive methods for HAVS risk management in the workplace.