A Predictive Model of the Stock Market Using the LSTM Algorithm with a Combination of Exponential Moving Average (EMA) and Relative Strength Index (RSI) Indicators

This research paper has focused on the integration of promising stock market indicators such as the relative strength index (RSI) and different versions of the exponential moving average (EMA) (i.e., 50-day, 100-day, and 150-day EMA) with the long short-term memory (LSTM) machine learning algorithm for stock price prediction. LSTM is the most robust version of recurrent neural network because it can handle the "vanishing gradient" problem effectively and handle lengthy time series data. The selected dataset was taken from NSE India using Yahoo Finance. In our proposed research, we used RSI and EMA data along with basic features such as open, high, low, close, and volume (OHLCV) information. The selected technical indicators and OHLCV data act as input features for the LSTM model. The results show that the integration of technical indicators along with traditional OHLCV improves the performance of the stock closing price prediction model. The evaluation metrics used in this research are the RMSE, MAPE, and R² score. The improvements in the R² score and decreases in the RMSE and MAPE indicate that the proposed technique performs well in stock closing price prediction. The proposed technique helps to improve intraday trading by predicting the closing price of the stock for the next day and the trends of selected stocks in the near term.