<p>Financial Risk Management (FRM) is increasing rapidly with integration of Machine Learning (ML) models with advanced techniques for interconnecting and managing critical financial data. The losses and maximized profits are managed by financial risk management. Therefore, it is important to most businesses. Still, traditional methods cannot predict financial risk accurately. The financial risk is identified by using this proposed system. machine learning based financial risk management using hierarchical clustering will accurately identify the risk. This proposed system uses Company Bankruptcy Prediction Dataset from Kaggle. The identified risk is shared across all the departments by using communication and coordination, and it also identifies sources of risk, market fluctuations. Feature selection contains correlation-based feature filtering. Hierarchical clustering is used to group similar financial risk patterns into clusters, which enables effective risk segmentation. The financial risk is assessed by extracting relevant features, and then statistical evaluations will applied. This proposed system uses machine learning algorithm (XGBOOST (Extreme Gradient Boosting) + Support Vector Machine (SVM) (hybrid model)) to identify financial risks and to determine whether they are risky or non-risky based on financial data. In this proposed system, XGBoost handles non-linear and imbalanced data, while SVM improves decision boundary generalization. The possibility of the risk is also evaluated along with its frequency. This model also shows its impact on company/organization/institution. Hence, it determines the overall risk level. Therefore, this proposed system shows better results in terms of accuracy, precision, recall, and F1-score.</p>