Abstract
The trend prediction of the stock is a main challenge. Accidental factors often lead to short-term sharp fluctuations in stock markets, deviating from the original normal trend. The short-term fluctuation of stock price has high noise, which is not conducive to the prediction of stock trends. Therefore, we used discrete wavelet transform (DWT)-based denoising to denoise stock data. Denoising the stock data assisted us to eliminate the influences of short-term random events on the continuous trend of the stock. The denoised data showed more stable trend characteristics and smoothness. Extreme learning machine (ELM) is one of the effective training algorithms for fully connected single-hidden-layer feedforward neural networks (SLFNs), which possesses the advantages of fast convergence, unique results, and it does not converge to a local minimum. Therefore, this paper proposed a combination of ELM- and DWT-based denoising to predict the trend of stocks. The proposed method was used to predict the trend of 400 stocks in China. The prediction results of the proposed method are a good proof of the efficacy of DWT-based denoising for stock trends, and showed an excellent performance compared to 12 machine learning algorithms (e.g., recurrent neural network (RNN) and long short-term memory (LSTM)).
Highlights
In the era of big data, deep learning for predicting stock prices [1] and trends has become more popular [2,3]
Due to the applicability of wavelet transform in financial data, as well as the need for data smoothing of the labeling method based on the continuous trend of stock data, and with respect to the advantages of Extreme learning machine (ELM), we proposed a hybrid method for stock trend prediction based on ELM and wavelet transform
ELMare is randomly a new algorithm developed for single-hidden-layer feedforward neural networks (SLFNs) algorithm, the input layer weights assigned, and the output layer weights obtained by using layer weights are randomly assigned, and the output layer weights are obtained by using the generalized inverse of the hidden layer output matrix
Summary
In the era of big data, deep learning for predicting stock prices [1] and trends has become more popular [2,3]. Xu et al presented design and implementation of a stacked system to predict the stock price Their model used the wavelet transform technique to reduce the noise of market data, and stacked auto-encoder to filter unimportant features from preprocessed data [60]. He et al proposed a new shrinkage (threshold) function to improve the performance of wavelet shrinkage denoising [61]. The on the is third section,and an overview of the continuous labeling method based statistical metrics used for evaluation of experimental results are described, and the reatime-series data is presented, and the stock datasets used in this paper are introduced. The descriptions of the related abbreviations are listed in Appendix A Table A1
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have