The number of vulnerabilities is increasing daily, and organisations are flooded by vulnerabilities in their IT environment. The increasing number of vulnerabilities in organisations' IT environments presents a significant challenge, requiring effective identification and prioritisation of critical vulnerabilities. Different techniques exist to this date, such as CVSS scoring or Risk-based scoring from solution providers to perform prioritisation of vulnerabilities. However, large industries with extensive assets often face difficulty in managing and fixing a large pool of vulnerabilities, as traditional techniques tend to classify numerous vulnerabilities as high or critical. This study proposes a machine learning model based on the K-means++clustering technique that leverages vulnerability data and asset financial value assessments to find patterns within vulnerability and group the most critical vulnerabilities. Our study successfully determined a group of the most critical vulnerabilities from a sample dataset of vulnerabilities from one of the large organisations. By considering the financial value of assets, our solution demonstrates a more accurate prioritisation, enabling organisations to allocate resources effectively and address the most critical vulnerabilities first. This study enhances vulnerability management practices in large organisations and serves as a foundation for further research and development in vulnerability prioritisation using machine learning techniques