Stock Trend Prediction Using LSTM with MA, EMA, MACD and RSI Indicators

Abstract

The stock market that has been known volatile is always an attractive target for the researchers to perform research and experiment on. Stock trend prediction is one of the most famous topics that is done as the movement of a stock is full of uncertainty and is affected by many different factors. In this research, the technical indicator of a stocks has been utilized (MA, EMA, RSI and MACD) to get the signal of the upcoming trend of a stock in order to achieve stock trend prediction. Machine learning techniques is also applied to process those stock data and stock indicator. The technique that is proposed to develop the stock prediction model is the Long Short Term Memory Neural Network, also known as LSTM. After the model is developed, it will be used to carry out prediction on stock and compare the actual stock movement with the predicted stock movement to find out its accuracy in making stock trend prediction. Three stocks will be used to validate the performance of the model which are Public Bank, Tenaga, and Apex Healthcare. The results show that the trend of the inspected stocks are successfully predicted using the LSTM model.