Stock price prediction method based on genetic algorithm and long-short-term neural network

A neural network and genetic algorithm technology, applied in biological neural network models, genetic laws, market forecasting, etc., can solve problems such as the timeliness and difference of financial data that cannot be solved, and achieve the effect of improving forecasting accuracy.

Pending Publication Date: 2021-02-26
ZHEJIANG NORMAL UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Second, difference
Random forest and support vector machine algorithms cannot solve the timeliness and variance of financial data

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
  • Stock price prediction method based on genetic algorithm and long-short-term neural network
  • Stock price prediction method based on genetic algorithm and long-short-term neural network
  • Stock price prediction method based on genetic algorithm and long-short-term neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The embodiments of the present invention are implemented on the premise of the technical solutions of the present invention, and detailed implementation methods and specific operation processes are given, but the protection scope of the present invention is not limited to the following embodiments.

[0029] The detailed steps are as follows:

[0030] Step 1: Collect the historical data of all original factors of China Construction Bank from January 1, 2010 to April 1, 2020, and perform data preprocessing such as normalization and missing value processing;

[0031] Step 2: Use the genetic algorithm to perform feature selection on all factors to obtain the optimized factor combination;

[0032] Step 3: Set the LSTM network structure, determine the hyperparameters, and randomly initialize the hidden layer parameters;

[0033] Step 4: Normalize the input data and train the LSTM stock prediction model on the training set;

[0034] Step 5: Input the test set data into the 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

According to the method, feature selection is carried out on massive stock factors based on a genetic algorithm (GA), an optimal factor combination suitable for a current scene is selected, and deep learning is carried out by adopting a long-short-term neural network model (LSTM), so that high-precision prediction of the stock price is achieved. According to the genetic algorithm, an adaptive heuristic search mechanism is introduced based on natural selection and genetic evolution thought, and an approximately optimal solution of an optimization problem with a large search space is searched. In the population propagation process, combination crossover and variation are carried out by means of a genetic operator of natural genetics, and according to the principle of survival of fittest andelimination of advantages and disadvantages, an increasingly good approximate solution is generated through generation-by-generation evolution. The long-term and short-term neural network model is widely applied to a time sequence prediction model due to long-term memorability, and the prediction precision can be effectively improved by searching for the complex nonlinear relationship between thestock factor and the stock price through deep learning.

Description

technical field [0001] The invention relates to the field of deep learning, constructs a stock price prediction method based on a genetic algorithm and a long-short-time neural network, and can effectively improve stock prediction accuracy. Background technique [0002] With the rapid development of social economy, the number of listed companies is increasing, and stocks have become one of the hot topics in the financial field. The changing trend of stocks often affects the direction of many economic behaviors to a certain extent. Therefore, the stock price forecast It has also attracted the attention of more and more scholars. There are many factors that affect stock prices. With the maturity of statistical techniques in the financial field, financial scholars have excavated a large number of stock market impact factors and quantified them into specific data for research on stock trends. [0003] With the support of massive financial data, it is possible for the realizatio...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q40/04G06Q30/02G06N3/12G06N3/04
CPCG06Q40/04G06Q30/0206G06N3/126G06N3/044G06N3/045
Inventor 周昌军陈诗乐
Owner ZHEJIANG NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products