Design and Evaluation of Automatic Agents for Stock Market Intraday Trading

Automated trading has become very popular in electronic markets, such as stock market. The design and evaluation of trading agents are not trivial due to the complexity and dynamics of this scenario. Using an actual and reliable dataset from the Brazilian Stock Exchange, and aiming to support the Market Making process in High-Frequency Trading, in this work we design and evaluate some models of automated agents for stock market intraday trading. The modeled strategies are inspired by the Elliot Wave Principle and based on some technical concepts commonly used by stock market analysts. The results are promising, besides it is clearly that financial gains are not trivial to acquire. A variety of results were observed, part of them providing gains for all assets in specific trading days, and other part showing losses for other trading days. A rich experimental analysis provide interesting findings and insights, which will contribute for designing more effective trading agents.