A stock price prediction method based on an APSO-BP neural network

A technology of APSO-BP and BP neural network, which is applied in the field of stock price prediction based on APSO-BP neural network, can solve the problems of prediction model performance not up to expectations, slow convergence speed, easy to fall into local extremum, etc. The effects of falling into local extremum, improving prediction accuracy, and improving global search ability

Inactive Publication Date: 2019-06-21
HANGZHOU DIANZI UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional BP neural network imitates the working mode of neurons from a physiological point of view to a certain extent, and can approach nonlinear complex functions arbitrarily, but it is easy to fall into local extremum and slow convergence speed, which leads to the performance of the prediction model not meeting expectations

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A stock price prediction method based on an APSO-BP neural network
  • A stock price prediction method based on an APSO-BP neural network
  • A stock price prediction method based on an APSO-BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with drawings and embodiments.

[0041] figure 1 Shown is the prediction system model of the present invention, and the data used in the prediction model are respectively the opening price, the highest price, the lowest price, the closing price, the trading volume, and the trend of the next day of a certain stock. In this paper, the trend of the next day is the classification label, and the classification label is assigned according to the closing price, C t+1 represents the closing price on day t+1, then the training label y on day t t It can be calculated by the following formula:

[0042]

[0043] If the closing price of the next day is greater than today's closing price, it is judged to be up, represented by 1, otherwise it is judged to be down, represented by -1.

[0044] After inputting the stock data, use the APSO algorithm to optimize each weight and threshold in the BP neural network. T...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a stock price prediction method based on an APSO-BP neural network, which comprises the steps of data preprocessing and APSO-BP neural network prediction model construction. The method comprises the following steps: firstly, extracting effective features from collected stock data, and performing data preprocessing to form a feature data sample set; Then, constructing an appropriate BP neural network model; optimizing the initial weight and the threshold value of the BP neural network by using an adaptive mutation particle swarm optimization (APSO) algorithm to obtain the final APSO-BP neural network prediction model. The method is higher in prediction precision, does not fall into a local extreme value, is high in convergence speed, is short in prediction time, andis higher in execution efficiency.

Description

technical field [0001] The invention belongs to the field of machine learning (Machine Learning, ML), and mainly relates to a stock price prediction method, especially a stock price prediction method based on APSO-BP neural network. Background technique [0002] With the continuous heating up of machine learning research, machine learning has also been widely used in the field of financial time series, because artificial neural networks have outstanding ability to deal with nonlinear problems, strong fitting ability, good predictability and Practicality, in some fields to get more accurate prediction results, so more and more researchers combine it with financial time series and apply it to stock trend prediction. Machine learning can organize and dig out the hidden laws and valuable information of the time series itself from a large amount of historical data, providing effective technical support for investors to obtain differential profits. Although there are many financi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/04G06Q40/04G06N3/04G06N3/08
Inventor方昕侯怡岑
OwnerHANGZHOU DIANZI UNIV