COMBINATION OF DEEP-LEARNING MODELS TO FORECAST STOCK PRICE OF AAPL AND TSLA

Abstract

Deep Learning is a promising domain. It has different applications in different areas of life and its application on the stock market is widely used due to its efficiency. Long Short Term Memory (LSTM) proved its efficiency in dealing with time-series data due to the unique hidden unit structure. This paper integrated LSTM with attention mechanism and sentiment analysis to forecast the closing price of two stocks; namely, APPL and TSLA, from the NASDAQ stock market. We compared our hybrid model with LSTM, LSTM with sentiment analysis and LSTM with Attention Mechanism. Three benchmarks were used to measure the performance of the models; the first one is Mean Square Error (MSE), the second one is Root Mean Square Error (RMSE) and the third one is Mean Absolute Error (MAE). The results show that the hybridization is more accurate than the LSTM model alone.