Trading Policy

Trading policy research focuses on optimizing asset buying and selling strategies to maximize returns and minimize risk within financial markets. Current research emphasizes the development and refinement of machine learning models, including reinforcement learning and supervised/unsupervised learning techniques like Random Forests and K-Nearest Neighbors, to predict market movements and improve trade execution. This work addresses challenges like overfitting in reinforcement learning and the need for robust, generalizable algorithms capable of handling market regime shifts and diverse data sources, ultimately aiming to improve portfolio management and trading efficiency.