Bankruptcy prediction plays a vital role in financial risk management by identifying companies that may face financial distress in the future. Early prediction helps investors, financial institutions, and policymakers take preventive actions and minimize financial losses. Traditional statistical methods often fail to capture complex relationships among financial indicators, which limits their prediction capability. To overcome this challenge, this study proposes a bankruptcy prediction system using hybrid machine learning techniques. The system analyzes various financial ratios and organizational indicators to classify companies as bankrupt or non-bankrupt. Data preprocessing techniques such as normalization and feature selection are applied to improve model performance. Multiple machine learning algorithms are integrated to form a hybrid model that enhances prediction accuracy and reliability. The experimental results demonstrate that the proposed model achieves an accuracy of 96.83% and an AUC score of 98.68%, indicating strong classification performance. In addition, a web-based interface is developed to allow users to train models, view datasets, and perform real-time bankruptcy predictions. The proposed system provides an effective decision-support tool for financial risk assessment and corporate sustainability analysis