Forecasting multistep daily stock prices for long-term investment decisions: A study of deep learning models on global indices

Abstract

Deep machine learning algorithms play an important role in facilitating the development of predictive models for the stock market. However, most studies focus on predicting next-day stock prices or movements, limiting the usability of the predictive model for investors. This study extensively explores the ability of deep learning models to predict out-of-sample the daily prices of global stock indices over a long term, up to a year. The performance of six models, including Deep Neural Network (DNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN), are compared using Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The models predict the long-term daily prices of five global stock indices, namely the Nifty, the Dow Jones Industrial Average (DJIA), the DAX performance index (DAX), the Nikkei 225 (NI225), and the Shanghai Stock Exchange composite Index (SSE). The results confirm the superiority of LSTM for predicting long-term daily prices. The Bi-LSTM does not improve the result of LSTM but performs better than other algorithms. CNN overfits the training data and poorly forecasts the long-term stock prices of global indices on the testing data. This research demonstrates the potential of deep learning models for long-term stock price forecasting, offering valuable insights for investors. Additionally, the patterns of predicted daily prices can be helpful in building trading and risk management decision systems.