Scholarlink

In recent years, there has been growing interest in applying neural network architectures to financial prediction. This study aims to examine the utilization of a Long Short-Term Memory (LSTM) model trained on both quarterly fundamental data and daily historical stock price data of Apple Inc. (AAPL). The study evaluates the accuracy of various LSTM model variations, trained on 29 distinct fundamental indicators, using Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) for predicting future stock prices. The results show that by selectively choosing the fundamental indicators for training the LSTM model based on fundamental analysis, it can achieve a higher accuracy in comparison to a LSTM model trained exclusively on historical price data.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Recurrent Neural Networks for Apple Stock Price Prediction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Bin Melville Huang,
  • Lifeng Liu,
  • Lipo Wang,
  • Yaoli Wang

摘要

In recent years, there has been growing interest in applying neural network architectures to financial prediction. This study aims to examine the utilization of a Long Short-Term Memory (LSTM) model trained on both quarterly fundamental data and daily historical stock price data of Apple Inc. (AAPL). The study evaluates the accuracy of various LSTM model variations, trained on 29 distinct fundamental indicators, using Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) for predicting future stock prices. The results show that by selectively choosing the fundamental indicators for training the LSTM model based on fundamental analysis, it can achieve a higher accuracy in comparison to a LSTM model trained exclusively on historical price data.