Wilfredo Tovar

Deep Learning Based on Generative Adversarial and Convolutional Neural Networks for Financial Time Series Predictions

This paper proposes the implementation of a generative adversarial network (GAN), which is composed by a bi-directional Long short-term memory (LSTM) and convolutional neural network(CNN) referred as Bi-L STM-CNN to generate synthetic data that agree with existing real financial data so the features of stocks with positive or negative trends can be retained to predict future trends of a stock.