Cross asset trading system controls portfolio losses reliably
CAST: A Cross-Asset State-Space Trading System for Drawdown Control in Stock Markets
Computational Engineering, Finance, and Science
Summary
Investment portfolios often face the problem of losing too much value during bad market times, which can threaten their long-term success. The authors created CAST, a trading system that looks at multiple stocks together and predicts their hidden market states by considering how they relate to each other. CAST then uses these predictions to decide trades in a way that controls risk by explicitly limiting how much value can drop. Tested over 15 years and during crisis periods, CAST showed it can achieve good returns with smaller losses than other methods. Its design is modular, letting different parts be swapped or understood independently.
What this means in practice
- •For quantitative traders: Use CAST to manage portfolio drawdowns while trading multiple stocks adaptively with risk-aware control of trade decisions.
- •For energy grid operators: Implement CAST’s state-space and control framework to predict and adjust cross-regional power flows under uncertainty.
Authors
Yu Peng, Matloob Khushi, Josiah Poon
Abstract
Managing drawdown, the peak-to-trough decline in an investment portfolio's value, is a precondition for long-term survival in practical investment management. However, mainstream stock forecasting methods predominantly optimize returns or Sharpe ratios under the independent and identically distributed (i.i.d.) assumption. Real markets do not follow this assumption, triggering catastrophic drawdowns. We propose a cross-asset state-space trading system (CAST), consisting of two components: The predictor, Cross-Asset Collaborative Kalman Filter (CoKF), estimates each asset's latent state online, coupling all assets through their correlations and adaptively fusing multiple integrated-random-walk orders. The controller, Model Predictive Control (MPC), converts the predictor's forecast into trades, using forecast uncertainty as an explicit risk penalty that controls drawdown. We evaluate CAST on four real-world stock markets over a 15-year test window and show that it consistently occupies the return-drawdown Pareto frontier, achieving strong risk-adjusted performance while maintaining substantially lower maximum drawdown than competitive baselines. A stress test across crisis periods further demonstrates robust behavior under market shocks and distribution shift. Because the predictor and controller interact only through the predicted price path, both are plug-and-play, making CAST a modular, interpretable trading system. The code is available at https://github.com/FanBroWell/CAST