Open AccessStock Trading Classifier with Multichannel Convolutional Neural Network
Author(s) -
Davi Nascimento,
Anna Helena Reali Costa,
Reinaldo A. C. Bianchi
Publication year - 2020
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/eniac.2020.12136
Subject(s) - convolutional neural network , computer science , stock market , stock (firearms) , artificial intelligence , classifier (uml) , machine learning , deep learning , artificial neural network , trading strategy , algorithmic trading , econometrics , finance , business , economics , engineering , mechanical engineering , paleontology , horse , biology
Stock market forecasting has been a quite popular challenge in machine learning research. Recently, studies have been using deep learning techniques, such as Convolutional Neural Networks (CNN), to perform regression on the prices or classification on trading signal as an operation indication. However, they did not reach a satisfactory financial result. In this work we aim to design a financially profitable stock market method by proposing a novel approach called Multichannel CNN Trading Classifier (MCNN-TC). The model was evaluated using data from the Brazilian stock market. The results indicate a satisfactory financial trading performance compared to the Buy and Hold strategy and good classification metrics.