Comparing LSTM Models for Stock Market Prediction: A Case Study with Apple’s Historical Prices

Stock market prediction holds significant importance in the world of finance, captivating the attention of both investors and financial researchers. The integration of artificial intelligence and advancements in computational power has led to substantial improvements in predicting stock prices, surpassing the effectiveness of traditional programmed prediction methods. In this paper, we explore three distinct and innovative methods for stock price prediction: Long Short-Term Memory (LSTM), LSTM combined with Simple Moving Average (LSTM-SMA), and LSTM combined with Exponential Moving Average (LSTM-EMA). Our analysis is conducted using a comprehensive historical dataset of Apple’s stock prices, and the performance of each model is rigorously evaluated using critical metrics, including Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R2 score. Additionally, the training time for each model is taken into account. The results show that all three models LSTM, LSTM-SMA, and LSTM-EMA give good prediction results for Apple’s stock price, in which the LSTM model gives the best prediction results for the 21-day cluster. However, in terms of computational time, the LSTM-SMA model and LSTM-EMA model are more efficient than the LSTM model. These findings highlight the potential of integrating advanced techniques to achieve more accurate and efficient stock price predictions.