Group decision stock price trend insight method based on graphic feature library

A graphical feature, group decision-making technology, applied in instruments, finance, character and pattern recognition, etc., can solve the problems of NP difficulty, lack of mathematical interpretability of neural network stock price prediction, affecting the accuracy and efficiency of stock price prediction

Inactive Publication Date: 2020-11-20
山西墨丘利科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The above work all strives to use different methods to analyze and predict financial time prediction, but there are still some shortcomings: 1. The stock price prediction based on neural network lacks reasonable mathematical explainability, and the assumption of "complete rationality" for investors based on behavioral analysis , investors cannot make decisions based on the explained information; 2. Almost all of the above models use a global model (using all data for model building) for prediction or analysis
Among them, the minimum construction of the graph feature library directly affects the accuracy and efficiency of stock price prediction, and this problem is NP-hard

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
  • Group decision stock price trend insight method based on graphic feature library
  • Group decision stock price trend insight method based on graphic feature library
  • Group decision stock price trend insight method based on graphic feature library

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0031] Step 1: In this embodiment, a candidate graphic feature library is first constructed, which mainly includes two aspects, one is to standardize stock data mapping; the other is to select representative stock trend graphics to build a graphic feature library;

[0032] Step 11: Since the prices of different stocks vary greatly, it is necessary to standardize the stock transaction data for mapping. This patent uses a moving average function F To standardize the original data, the mathematical principle of the moving average algorithm is as follows:

[0033] ,

[0034] EMA( t )for t Day moving average, EMA ( t -1) is yesterday's moving average, n is the period, and price is the original price sequence. t sky map t different weights, when t =1, EMA( t )=price. It can be seen from the above formula that the moving average function EMA can make more effective use of historical data than directly using stock trading prices:

[0035] ,

[0036] EMA( t 1) is the fa...

specific Embodiment approach 2

[0087] Different from the specific embodiment 1, in the selection of the standardized function of the stock daily trading data in this embodiment, step 1 can use well-known stock technical indicators to standardize the stock price mapping, such as CCI indicators, KDJ indicators, MACD indicators, etc. .

specific Embodiment approach 3

[0089] Different from Embodiment 1 or Embodiment 2, the stock trading data selected by the candidate graphic reference data in this embodiment can be any time period, such as 1 second, 5 seconds, 30 seconds, 60 seconds, 120 seconds, week, month, Correspondingly, the price prediction cycle of the stock to be predicted is also the same as the time cycle selected in the graphic feature library, so that this patent can realize the prediction of the full time cycle of the stock.

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

Stock price estimation belongs to the field of financial big data analysis and stock investment. An existing stock price prediction method either lacks reasonable mathematical interpretability (such as stock price prediction based on deep learning) or is difficult to evolve a model in real time according to the time sequence change of the stock price. The invention discloses a group decision stockprice trend insight method based on a graphic feature library. The method aims to construct a stock price or a graphic feature library after standardized mapping through stock transaction historicaldata. And after the to-be-predicted stock is subjected to standardization and wavelet de-noising smoothing, similarity calculation is performed on the graphical to-be-predicted stock and graphs in thegraph feature library by adopting a dynamic time warping algorithm, and a group decision algorithm is introduced to estimate the future stock price of the target stock by using the similar graphs. The minimized construction of the graphic feature library directly influences the precision and efficiency of stock price prediction; the problem is an NP problem, the invention provides a heuristic algorithm based on a greedy strategy to realize approximation of minimization of a graphic feature library, and a graphic base in the graphic feature library can be adaptively adjusted according to incremental change of financial data.

Description

technical field [0001] The invention relates to the fields of financial big data analysis and stock investment, in particular to a group decision-making stock price trend insight method based on a graph feature library. Background technique [0002] As an important part of the financial market, the stock market has played an important role in promoting my country's economic reform and economic development. The stock market price fluctuation is the basis of the stock market and the focus of stock investors. Therefore, the study of stock market price fluctuations can effectively control the laws of the stock market, enhance the stability of the financial market, and provide a certain basis for investors to make correct investment decisions. For the analysis of stock market price fluctuations, it is currently divided into two systems, one of which is based on various technical indicators of stocks to demonstrate stock trends, trading and other analysis methods. This type of me...

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): G06Q10/04G06Q40/04G06Q40/06G06K9/62
CPCG06Q10/04G06Q40/04G06Q40/06G06F18/22
Inventor周志刚白增亮罗继伟李文琴
Owner山西墨丘利科技有限公司