Portfolio optimization in the financial market with regime switching under constraints and transaction costs using model predictive control

<p style='text-indent:20px;'>A stock portfolio is a collection of assets owned by investors, such as companies or individuals. The determination of the optimal stock portfolio is an important issue for the investors. Management of investors' capital in a portfolio can be regarded as a dynamic optimal control problem. At the same time, the investors should also consider about the prediction of stock prices in the future time. Therefore, in this research, we propose Geometric Brownian Motion-Kalman Filter (GBM-KF) method to predict the future stock prices. Subsequently, the stock returns will be calculated based on the forecasting results of stock prices. Furthermore, Model Predictive Control (MPC) will be used to solve the portfolio optimization problem. It is noticeable that the management strategy of stock portfolio in this research considers the constraints on assets in the portfolio and the cost of transactions. Finally, a practical application of the solution is implemented on 3 company's stocks. The simulation results show that the performance of the proposed controller satisfies the state's and the control's constraints. In addition, the amount of capital owned by the investor as the output of system shows a significant increase.</p>

Download Full-text

Portfolio Optimization Under Regime Switching and Transaction Costs: Combining Neural Networks and Dynamic Programs

INFORMS Journal on Optimization ◽

10.1287/ijoo.2021.0053 ◽

2021 ◽

Author(s):

Xiaoyue Li ◽

John M. Mulvey

Keyword(s):

Neural Network ◽

Neural Networks ◽

Differential Equations ◽

Transaction Costs ◽

Portfolio Optimization ◽

Regime Switching ◽

Optimal Solution ◽

Combined Method ◽

Traditional Methods ◽

Dynamic Programs

The contributions of this paper are threefold. First, by combining dynamic programs and neural networks, we provide an efficient numerical method to solve a large multiperiod portfolio allocation problem under regime-switching market and transaction costs. Second, the performance of our combined method is shown to be close to optimal in a stylized case. To our knowledge, this is the first paper to carry out such a comparison. Last, the superiority of the combined method opens up the possibility for more research on financial applications of generic methods, such as neural networks, provided that solutions to simplified subproblems are available via traditional methods. The research on combining fast starts with neural networks began about four years ago. We observed that Professor Weinan E’s approach for solving systems of differential equations by neural networks had much improved performance when starting close to an optimal solution and could stall if the current iterate was far from an optimal solution. As we all know, this behavior is common with Newton- based algorithms. As a consequence, we discovered that combining a system of differential equations with a feedforward neural network could much improve overall computational performance. In this paper, we follow a similar direction for dynamic portfolio optimization within a regime-switching market with transaction costs. It investigates how to improve efficiency by combining dynamic programming with a recurrent neural network. Traditional methods face the curse of dimensionality. In contrast, the running time of our combined approach grows approximately linearly with the number of risky assets. It is inspiring to explore the possibilities of combined methods in financial management, believing a careful linkage of existing dynamic optimization algorithms and machine learning will be an active domain going forward. Relationship of the authors: Professor John M. Mulvey is Xiaoyue Li’s doctoral advisor.

Download Full-text