Forecasting stock prices in two ways based on LSTM neural network

作者：Jingyi Du, Qingli Liu, Kang Chen, Jiacheng Wang · 发表于：2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · 年份：2019 · DOI：10.1109/itnec.2019.8729026 · 被引用次数：39 · 研究领域：Stock Market Forecasting Methods、Energy Load and Power Forecasting、Time Series Analysis and Forecasting

Due to the extensive application of deep learning in processing time series and recent progress, LSTM (Long Short-Term Memory) neural network is the most commonly used and most powerful tool for time series models. The LSTM neural network is used to predict Apple stocks by using single feature input variables and multi-feature input variables to verify the prediction effect of the model on stock time series. The experimental results show that the model has a high accuracy of 0.033 for the multivariate input and is accurate, which is in line with the actual demand. For the univariate feature input, the predicted squared absolute error is 0.155, which is inferior to the multi-feature variable input.