In conclusion, the AI-based portfolio can surpass experienced human traders in financial markets. Their results suggest that AI-based portfolio systems outperform human analysts and are a valuable, alternative information intermediary to traditional sell-side analysts for investment decisions. provided the first comprehensive comparison of the investment recommendations generated by AI-based and human analysts. However, AI-based investment has the advantages of low thresholds, low costs, and high efficiency and revises recommendations more often than human analysts. At the same time, they are more vulnerable to behavioral biases and conflicts of interest. Traditional investment analysts fail to serve a large number of low net worth customers. Some portfolio results recommended by traditional investment analysts present several limitations. However, the efficiency of such portfolio management is extremely low in a complex and risky stock market. Professional investment analysts and retail investors often make stock trading decisions based on their personal experience and views. Portfolio management is a continuous process that maximizes accumulated profits by minimizing the overall risk of the portfolio and involves position sizing and resource allocation. In view of the existence of various factors in the stock market, rational portfolio management is our main goal. Due to the instability and extremely unpredictable features of the stock market, stock decision-making is also affected by various and conflicting attributes, resulting in a typical multiattribute decision-making (MADM) problem. Many factors affect the stock market, such as political turmoil, news events, public sentiment, and exchange rate fluctuations. The stock market is a highly complex and nonlinear dynamic ecosystem composed of market participants who can make decisions freely based on their individual beliefs and personal profits. In terms of diversified investment, stock investment is considered to be the most difficult. As the saying goes, “Don’t put all your eggs in one basket.” Generally, diversification is considered a safer way to invest one’s money in multiple assets rather than a single asset. To reduce the risks of the investment process, one must weigh and allocate one’s money considering a variety of factors. Warren Buffett, a famous investor, defines investment as “A process of laying out money now in the expectation of receiving more money in the future.” Indeed, successful investing can increase one’s finances through a variety of investment tools. Investing undoubtedly increases one’s source of income and improves one’s personal quality of life. Investing is a means to save money from extra income and idle funds, resulting in more compensation and rewards in the future. The experimental results show that the annualized return, cumulative return, and Sharpe ratio values of our ensemble strategy are higher than those of the baselines, which indicates that our nested RL and WRSC methods can assist investors in their portfolio management with more profits under the same level of investment risk. All the algorithms are validated for the U.S., Japanese and British stocks and evaluated by different performance indicators. In this way, investors can gain more profits by integrating the advantages of all agents. Second, to inherit the advantages of three basic decision-makers, we consider confidence and propose a weight random selection with confidence (WRSC) strategy. Thus, this strategy can dynamically select agents according to the current situation to generate trading decisions made under different market environments. First, we propose a nested reinforcement learning (Nested RL) method based on three deep reinforcement learning models (the Advantage Actor Critic, Deep Deterministic Policy Gradient, and Soft Actor Critic models) that adopts an integration strategy by nesting reinforcement learning on the basic decision-maker. In this paper, we propose two stock trading decision-making methods. In a complex and changeable stock market, it is very important to design a trading agent that can benefit investors.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |