DU-TTT: Decision-Utility Test-Time Training for Portfolio Construction with Delayed Feedback

A deployed return forecaster must adapt online to non-stationary environments. Standard test-time training (TTT) strategies fail here for two reasons: misalignment, as mean-squared error ignores decision boundaries and portfolio mechanics, and delayed, constrained feedback, as labels arrive $h$ days later under strict leverage and fee constraints. To address these challenges, we propose Decision-Utility Test-Time Training (), which adapts a lightweight affine head on a frozen feature extractor directly using downstream portfolio utility. buffers historical decision contexts, evaluates matured $h$-day returns, and updates the adaptation head via a covariance-weighted utility gradient. To focus feedback where it matters most, incorporates a soft top-$K$ selection mechanism, concentrating adaptation on the active trading margin while dynamically adjusting step size based on forecast dispersion. Evaluated across 109 equity universes over two distinct market regimes, consistently outperforms standard MSE-based adaptation in both portfolio growth and Sharpe ratio. Our analysis reveals that achieves its primary advantage by suppressing unrewarded turnover and trading friction. Furthermore, ablation studies confirm the necessity of both the margin-focused selection and dispersion-scaled step sizes. By directly aligning test-time adaptation with financial utility, offers a robust framework for real-world algorithmic trading under distribution shift.