This repository contains the implementation of an algorithmic trading system for the stock market. The goal is to develop a trading strategy that utilizes machine learning and technical analysis techniques to make informed trading decisions.
The project aims to optimize trading strategies using a combination of machine learning and technical analysis in the stock market. The implementation is based on the paper "Technical analysis strategy optimization using a machine learning approach in stock market indices" by Jordan Ayala, Miguel García-Torres, José Luis Vázquez Noguera, Francisco Gómez-Vela, and Federico Divina, published in the Knowledge-Based Systems journal in 2021 (DOI: 10.1016/j.knosys.2021.107119). The hybrid approach proposed in the paper combines technical indicators with machine learning models to generate trading signals. By leveraging machine learning techniques such as Linear Models (LM), Artificial Neural Networks (ANN), Random Forests (RF), and Support Vector Regression (SVR), the trading system aims to improve the effectiveness and competitiveness of the trading rules.
data/: Contains the necessary data files for backtesting and training the trading models.models/: Contains the implementation of machine learning models used for trading strategy optimization.strategies/: Contains the implementation of technical analysis strategies and their resultsmain/: Contains all the different parts put together (you only need to run this file)
We would like to acknowledge the authors of the paper "Technical analysis strategy optimization using a machine learning approach in stock market indices" for their valuable research and contributions.
Jordan Ayala, Miguel García-Torres, José Luis Vázquez Noguera, Francisco Gómez-Vela, Federico Divina. "Technical analysis strategy optimization using a machine learning approach in stock market indices." Knowledge-Based Systems, 2021. DOI: 10.1016/j.knosys.2021.107119