Date

The stock market is a volatile and nonlinear environment, making it difficult to predict returns accurately. However,

machine learning and deep learning models have been able to

achieve some degree of accuracy in predicting financial time

series. The recurrent neural networks (RNN) are derived from

the feedforward neural networks, a deep learning algorithm.

The cases of gradient vanishing and explosion are commonly

associated with the traditional RNNs. The Long-Short Term

Memory (LSTM) model is capable of eliminating the problems