عليرضا اصغري

The increasing use of technology in financial markets has led to extensive changes in conventional trading structures. One of these changes is the emergence of algorithmic trading. In algorithmic trading, buying and selling decisions are made by computer algorithms. The impact of algorithmic trading systems on different markets is not hidden from anyone. This impact is increasing every year. Today, most orders that reach exchanges are created by algorithmic trading agents. Today, machine learning-based methods play an important role in building automated trading systems. The increasing complexity and dynamism of financial markets are among the key challenges of these methods. This dynamic has led to the failure of most inflexible trading strategies. The most widely used machine learning approach is supervised learning, but in interactive environments such as the financial market, the use of supervised learning alone is not enough and has limitations such as: difficulty in defining appropriate labels and lack of modeling of the dynamic nature of the market. Due to the good performance of deep reinforcement learning based approaches in interactive environments, we will use these approaches to solve the mentioned problems. In this thesis, we presented a deep reinforcement learning framework for trading in the financial market, a set of input features and indicators selected and tailored to the purpose of the problem, reward function and appropriate models based on fully connected, convolutional and hybrid networks. The proposed top models traded under real market conditions such as transaction costs and then were eva‎luated. In addition to outperforming the buy and hold strategy, these models achieved excellent cumulative returns while having appropriate risk metrics.

يادگيري عميق , يادگيري تقويتي عميق , معامله الگوريتمي , بازار مالي , استراتژي معامله كمّي

Deep learning , Deep reinforcement learning , Algorithmic trading , Financial market , Quantitative trading strategy

Alireza Asghari

Dr. Nasser Mozayani