Model predictive control for multi-period portfolio optimization: a trading-oriented learning approach

Abstract

Portfolio optimization aims at finding the optimal allocation of a given wealth among different assets to maximize an investor's utility function. A major critical issue concerns the prediction of future asset returns to forecast market evolution, due to the non-stationarity and volatility of asset prices. In this work, a learning-based Model Predictive Control (MPC) strategy for multi-period portfolio optimization is proposed, where the return prediction model is estimated via a novel trading-oriented learning paradigm. According to such a perspective, the model parameters are not the ones minimizing the prediction error but those that directly maximize the investor's utility. An extensive experimental study carried out on real-market data shows the potential improvements introduced by the proposed methodology compared to benchmark financial strategies.

Keywords:

• Portfolio optimization
• learning MPC
• identification for control
• Bayesian optimization

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 Namely, the maximum percentage of the portfolio that one can transfer at each trading instant.

2 We denote the initial setting of the portfolio as ${\mathbf{w}}_0$, while the initial wealth is indicated as $V_0$.