Stock Prediction Model Based on Wavelet Denoising LSTM

• 1、School of Business Administration,Liaoning Technical University

Abstract：Stock is one of the important components of China\'s economy. With the rapid development of the national economy and the continuous improvement of people\'s investment awareness, more and more people participate in stock investment transactions. Therefore, accurate prediction and analysis of the trend of the stock market has become a major concern for people. With the advent of the era of big data, the rapid development of deep learning has been promoted. Recurrent neural networks have demonstrated excellent performance in the field of time series prediction. Long and short term memory network (LSTM) is one of the most classical models in cyclic neural networks, which can effectively predict stock time series. However, stock prices are susceptible to multiple factors. In order to minimize the interference of noise signals on prediction tasks in stock Stock Prediction Model Based on Wavelet Denoising LSTMprediction, a wavelet denoising LSTM prediction model is proposed. Before prediction, the wavelet threshold denoising method is first used to denoise the stock time series to remove the interference of abnormal signals on the series, and then the LSTM network is used to predict the stock opening price. Experiments show that compared with other network structures, the LSTM model based on wavelet denoising has more accurate prediction results and higher applicability.

Keywords： deep learning Wavelet noise reduction LSTM neural network Stock time series forecasting