Stock price prediction method and device based on wavelet transform and long-term and short-term memory neural network fusion
A long short-term memory, price prediction technology, applied in the field of data information, can solve the problems of Fourier transform difficulty, time-frequency localization, etc., to solve the gradient disappearance and gradient explosion, reduce the prediction error, and solve the time-frequency localization. the contradictory effect of
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0022] The present invention provides a stock price prediction method based on wavelet transform and long short-term memory neural network fusion, such as Figures 1 to 7 As shown, the methods include:
[0023] S1, perform wavelet decomposition on the stock sequence based on discrete wavelet transform;
[0024] Wavelet transform analysis is a sequence analysis method with time-frequency localization properties. The key is to decompose the sequence by wavelet. ψ(t) is a square integrable function, that is, ψ(t)∈L 2 , whose Fourier transform is like The following conditions:
[0025]
[0026] Then ψ(t) is called the base wavelet. After the basic wavelet undergoes stretching and translation operations, a new wavelet sequence is obtained, which is called a sub-wavelet:
[0027]
[0028] ψ a,b (t) is a wavelet basis function dependent on parameters a and b. Among them, a is the scaling factor or scale factor, and changing the size of a means doing scaling transform...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 



