Optimization of Portfolio Investment Strategy Based on Markov Decision Process Model

Abstract

With the continuous development of the world financial market, investors are often faced with a wide variety of assets but do not know how to choose. In order to obtain the maximum benefits, how to choose the optimal investment strategy has become a top priority. In this paper, based on Markov decision process model, we study the optimal strategy for investment with two important assets in the market, gold and Bitcoin. we solve the problem with a Markov decision process model and measure the risk of the trade by financial indicators such as deviation rates and bullish indicators. Then a difference-in-difference formula for the asset appreciation rate is introduced to optimize the model by incorporating the long-term impact of trading on assets. Also based on the iterative algorithm of the sample path, an iterative algorithm of the strategy that can be applied online is designed, and it was finally calculated that after five years of investment using this strategy under the initial condition of $1000, $348287.46 could be obtained.