Sistema de tomada de decisão no mercado de ações utilizando LGBM

Abstract

This work focuses on the study of the application of a machine learning model known as LGBM (Light Gradient Boosting Machine) in classifying the best buying moments of an asset in the Brazilian stock market, which works as a trading system. As predictor variables, technical market indicators calculated from the historical price series are used. To define the best buying moment of the asset, the three-barrier method is applied. Additionally, this work presents a practical approach with the inclusion of Take Profit and Stop Loss limits. The results obtained from the proposed model were compared with the Moving Average Crossover (MAC) trading strategy.