The model employs a voting mechanism among machine learning classifiers to non-linearly integrate various features, alongside techniques designed to reduce overfitting—a common issue with financial data characterized by a low signal-to-noise ratio. The features include time-varying stock-specific metrics, sector information, market regime indicators , and calendar-related anomalies. The model employs a voting mechanism among machine learning classifiers to non-linearly integrate various features, alongside techniques designed to reduce overfitting. Top US and European stocks are covered.