Multivariate anomalies refer to unusual patterns or data points that deviate from expected behavior across multiple variables simultaneously. This article explores machine learning techniques for detecting such anomalies in the joint movements of SPY (equities), TLT (long-term bonds), and GLD (gold). To identify these anomalies, we applied Isolation Forest, One-Class SVM, and Autoencoders. Continue reading Multivariate Anomaly Detection in Asset Returns: A Machine Learning Perspective