| Popis: |
In this paper, time series of numerical correlations and morphological similarities are analyzed. It is proposed to combine the correlation coefficient with a time-weighted dynamic time warping (DTW) distance to emphasize timeliness as a stock linkage numerical formula. Therefore, the problem of finding the connection relationship between stocks can be converted into a numerical representation problem of stock linkage, and a stock linkage prediction optimized model based on long short-term memory (LSTM) can be established. At the same time, in order to improve the prediction performance of the LSTM model for the time series of stock interconnection values, wavelet transform and denoising autoencoder are used to denoise and reconstruct the input samples, thereby achieving more accurate prediction and analysis of stock linkage. |
