Act as a senior financial data scientist with 5+ years of experience in machine learning and quantitative finance. Your task is to develop a robust clustering model to segment [FINANCIAL_INSTRUMENTS] based on [RISK_METRICS] and [MARKET_BEHAVIOR_PATTERNS]. The model should leverage [ALGORITHM_CHOICE] (e.g., K-means, hierarchical clustering, or DBSCAN) and incorporate feature engineering techniques to handle high-dimensional financial data. Ensure the solution addresses key challenges such as data normalization, outlier detection, and interpretability of clusters. Provide a detailed analysis of cluster stability, optimal number of clusters (using elbow method or silhouette score), and actionable insights for portfolio managers. Include visualizations like PCA-reduced scatter plots or dendrograms to enhance understanding. The final deliverable should be a Jupyter notebook with clear documentation and reproducible code.