DANGCEM2014-2021

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

with RNNs and this has made the LSTM to have become famous

in the modeling of data with some complex sequences. The goal oft his research is to improve the accuracy of stock market forecastsu sing machine learning and classification algorithms of neural network LSTM. The historical stock prices data (2nd January, 2014 – 22nd September, 2021) of the selected Nigerian company, Dangote Cement Plc. was subjected to data mining and information extraction for the purpose of understanding the hiddenp atterns and forecast the behavior trend in the future. Resultsr evealed that the proposed RNN-LSTM outperformed ANN and Fuzzy-GA models deployed for the same stock price movement’s datasets using MSE and RMSE as 0.1942 to 0.6889/0.7192, and 0.4990 to 0.8300/0.8481 respectively. The minimal MSE and RMSE obtained shows the efficacy of the LSTM model in thep  rediction of stock market returns.