Tag
A Columbia University paper introduces a strictly causal Hidden Markov Model that adapts to changing market regimes, achieving a 2.18 Sharpe ratio vs 1.18 for SPX buy & hold and reducing max drawdown from -14.62% to -5.43% during the 2025 selloff.
This paper proposes an end-to-end decision-focused learning framework for sparse tangent portfolio optimization that replaces discrete asset selection with a smooth top-k operator, enabling gradient flow through prediction and optimization to directly maximize Sharpe ratio.