LSTM-Based Deep Learning Model for Financial Market Stock Price Prediction

Abstract

Through methods such as machine learning and deep learning, artificial intelligence models can process and analyze large amounts of complex financial data to assist financial institutions in rapid and accurate analysis and decision-making, thereby improving the efficiency and quality of financial services. In this paper, a prediction model of gold stock price based on Bayesian network optimized Long short-term memory neural network (BO-LSTM) is proposed. By introducing Bayesian network to optimize the hyperparameters of LSTM model, the prediction accuracy and robustness of the model are improved. The empirical results show that the BO-LSTM model has a significant advantage in the gold stock price prediction task, which is better than the traditional LSTM model and the benchmark model. The results of this study strongly support the effectiveness of Bayesian networks in optimizing deep learning models, and demonstrate the potential and application prospect of BO-LSTM model in financial market forecasting. In addition, the study also points out future improvement directions, including optimizing data selection and improving model structure to more accurately describe the complex and volatile stock market.